Recovery analysis of data sharing systems under deferred dirty pagepropagation policies

In a multinode data sharing environment, different buffer coherency control schemes based on various lock retention mechanisms can be designed to exploit the concept of deferring the propagation or writing of dirty pages to disk to improve normal performance. Two types of deferred write policies are considered. One policy only propagates dirty pages to disk at the times when dirty pages are flushed out of the buffer under LRU buffer replacement. The other policy also performs writes at the times when dirty pages are transferred across nodes. The dirty page propagation policy can have significant implications on the database recovery time. In this paper, we provide an analytical modeling framework for the analysis of the recovery times under the two deferred write policies. We demonstrate how these policies can be mapped onto a unified analytic modeling framework. The main challenge in the analysis is to obtain the pending update count distribution which can be used to determine the average numbers of log records and data I/Os needed to be applied during recovery. The analysis goes beyond previous work on modeling buffer hit probability in a data sharing system where only the average buffer composition, not the distribution, needs to be estimated, and recovery analysis in a single node environment where the complexities on tracking the propagation of dirty pages across nodes and the buffer invalidation effect do not appear     

Characterization of database access pattern for analytic prediction of buffer hit probability

The analytic prediction of buffer hit probability, based on the characterization of database accesses from real reference traces, is extremely useful for workload management and system capacity planning. The knowledge can be helpful for proper allocation of buffer space to various database relations, as well as for the management of buffer space for a mixed transaction and query environment. Access characterization can also be used to predict the buffer invalidation effect in a multi-node environment which, in turn, can influence transaction routing strategies. However, it is a challenge to characterize the database access pattern of a real workload reference trace in a simple manner that can easily be used to compute buffer hit probability. In this article, we use a characterization method that distinguishes three types of access patterns from a trace: (1) locality within a transaction, (2) random accesses by transactions, and (3) sequential accesses by long queries. We then propose a concise way to characterize the access skew across randomly accessed pages by logically grouping the large number of data pages into a small number of partitions such that the frequency of accessing each page within a partition can be treated as equal. Based on this approach, we present a recursive binary partitioning algorithm that can infer the access skew characterization from the buffer hit probabilities for a subset of the buffer sizes. We validate the buffer hit predictions for single and multiple node systems using production database traces. We further show that the proposed approach can predict the buffer hit probability of a composite workload from those of its component files.     

Buffer analysis for a data sharing environment with skewed dataaccess

Examines the effect of skewed database access on the transaction response time in a multisystem data sharing environment, where each computing node has access to shared data on disks, and has a local buffer of recently accessed granules. Skewness in data access can increase data contention since most accesses go to few data items. For the same reason, it can also increase the buffer hit probability. We quantify the resultant effect on the transaction response time, which depends not only on the various system parameters but also on the concurrency control (CC) protocol. Furthermore, the CC protocol can give rise to rerun transactions that have different buffer hit probabilities. In a multisystem environment, when a data block gets updated by a system, any copies of that block in other systems' local buffers are invalidated. Combining these effects, we find that higher skew does not necessarily lead to worse performance, and that with skewed access, optimistic CC is more robust than pessimistic CC. Examining the buffer hit probability as a function of the buffer size, we find that the effectiveness of additional buffer allocation can be broken down into multiple regions that depend on the access frequency distribution     

Incorporating System Overhead in Queuing Network Models

Multiclass queuing network models of multiprogramming computer systems are frequently used to predict the performance of computing systems as a function of user workload and hardware configuration. This paper examines three different methods for incorporating operating system overhead in multiclass queuing network models. The goal of the resultant model is to provide an accurate account of the processing performance and the system CPU overhead of each of the several different types of jobs (batch, timesharing, transaction processing, etc.) that together make up the multiprogramming workload. The first method introduces an operating sysbtm workload consisting of a fixed number of jobs to represent system CPU overhead processing. The second method extends the jobs' CPU service requests to include explicitly the CPU overhead necessary for system processing. The third method employs a communicating set of user and system job classes so that the CPU overhead can be modeled by switching jobs from user to system class whenever they require system CPU service. The capabilities and accuracy of the three methods are assessed and compared against performance and overhead data measured on a Univac 1110 computer.     

Rapid transaction-undo recovery using twin-page storage management

A twin-page storage method, which is an alternative to the TWIST (twin slot) approach by A. Reuter (190) for rapid transaction-undo recovery is presented. In contrast to TWIST, the twin-page approach allows dirty pages in the buffer to be written at any instant onto a disk without the requirement of undo logging, and, when a transaction is aborted, no explicit undo is required. As a result, all locks accumulated by the aborted transaction can be released earlier, allowing other transactions waiting for the locks to proceed. Through maintenance of aborted transaction identifiers, invalid pages written by the aborted transaction coexist with other valid pages and are guaranteed not to be accessed by subsequent transactions. Instead of an explicit undo, most of the invalid pages are overwritten by subsequent normal updates. Performance in terms of disk I/O and CPU overhead for transaction-undo recovery is analyzed and compared with TWIST. It is shown that the presented method is particularly suited for applications where there are a large number of updates written onto disk when transactions are aborted, and there are frequent aborts     

CPU load prediction using neuro-fuzzy and Bayesian inferences

Ensuring adequate use of the computing resources for highly fluctuating availability in multi-user computational environments requires effective prediction models, which play a key role in achieving application performance for large-scale distributed applications. Predicting the processor availability for scheduling a new process or task in a distributed environment is a basic problem that arises in many important contexts. The present paper aims at developing a model for single-step-ahead CPU load prediction that can be used to predict the future CPU load in a dynamic environment. Our prediction model is based on the control of multiple Local Adaptive Network-based Fuzzy Inference Systems Predictors (LAPs) via the Naïve Bayesian Network inference between clusters states of CPU load time points obtained by the C-means clustering process. Experimental results show that our model performs better and has less overhead than other approaches reported in the literature.     

基于用户访问模式的Web预取算法

缩短Web访问中的用户感知时间,是Web应用中的一个重要问题,服务器需要预测用户未来的HTTP请求和处理当前的网页以提高Web服务器的响应速度,为此提出了一种基于用户访问模式的Web预取算法.该算法根据Web日志信息分析了用户的访问模式,并计算出Web页面间的转移概率,以此作为对用户未来请求预取的依据.实验结果表明,该预取算法能有效提高预测精度和命中率,有效地缩短了用户的感知时间.     

Asymptotic buffer overflow probabilities in multiclassmultiplexers: an optimal control approach

We consider a multiclass multiplexer with support for multiple service classes and dedicated buffers for each service class. Under specific scheduling policies for sharing bandwidth among these classes, we seek the asymptotic (as the buffer size goes to infinity) tail of the buffer overflow probability for each dedicated buffer. We assume dependent arrival and service processes as is usually the case in models of bursty traffic. In the standard large deviations methodology, we provide a lower and a matching (up to first degree in the exponent) upper bound on the buffer overflow probabilities. We introduce a novel optimal control approach to address these problems. In particular, we relate the lower bound derivation to a deterministic optimal control problem, which we explicitly solve. Optimal state trajectories of the control problem correspond to typical congestion scenarios. We explicitly and in detail characterize the most likely modes of overflow. We specialize our results to the generalized processor sharing policy (GPS) and the generalized longest queue first policy (GLQF). The performance of strict priority policies is obtained as a corollary. We compare the GPS and GLQF policies and conclude that GLQF achieves smaller overflow probabilities than GPS for all arrival and service processes for which our analysis holds. Our results have important implications for traffic management of high-speed networks and can be used as a basis for an admission control mechanism which guarantees a different loss probability for each class     

Enable back memory and global synchronization on LLC buffer

The last-level cache (LLC) shared by heterogeneous processors such as CPU and general-purpose graphics processing unit (GPGPU) brings new opportunities to optimize data sharing among them. Previous work introduces the LLC buffer, which uses part of the LLC storage as a FIFO buffer to enable data sharing between CPU and GPGPU with negligible management overhead. However, the baseline LLC buffer’s capacity is limited and can lead to deadlock when the buffer is full. It also relies on inefficient CPU kernel relaunch and high overhead atomic operations on GPGPU for global synchronization. These limitations motivate us to enable back memory and global synchronization on the baseline LLC buffer and make it more practical. The back memory divides the buffer storage into two levels. While they are managed as a single queue, the data storage in each level is managed as individual circular buffer. The data are redirected to the memory level when the LLC level is full, and are loaded back to the LLC level when it has free space. The case study of n-queen shows that the back memory has a comparative performance with a LLC buffer of infinite LLC level. On the contrary, LLC buffer without back memory exhibits 10% performance degradation incurred by buffer space contention. The global synchronization is enabled by peeking the data about to be read from the buffer. Any request to read the data in LLC buffer after the global barrier is allowed only when all the threads reach the barrier. We adopt breadth-first search (BFS) as a case study and compare the LLC buffer with an optimized implementation of BFS on GPGPU. The results show the LLC buffer has speedup of 1.70 on average. The global synchronization time on GPGPU and CPU is decreased to 38 and 60–5%, respectively.     

Managing Frequent Updates in R-Trees for Update-Intensive Applications

Managing frequent updates is greatly important in many update-intensive applications, such as location-aware services, sensor networks, and stream databases. In this paper, we present an R-tree-based index structure (called R^sb-tree, R-tree with semibulk loading) for efficiently managing frequent updates from massive moving objects. The concept of semibulk loading is exploiting a small in-memory buffer to defer, buffer, and group the incoming updates and bulk-insert these updates simultaneously. With a reasonable memory overhead (typically only 1 percent of the whole data set), the proposed approach far outperforms the previous works in terms of update and query performance as well in a realistic environment. In order to further increase buffer hit ratio for the proposed approach, a new page-replacement policy that exploits the level of buffered node is proposed. Furthermore, we introduce the concept of deferring threshold ratio (dtr) that simply enables deferring CPU- and I/O-intensive operations such as node splits and removals. Extensive experimental evaluation reveals that the proposed approach is far more efficient than previous approaches for managing frequent updates under various settings.     

A Scalable Asynchronous Cache Consistency Scheme (SACCS) for mobile environments

In the literature, there exit two types of cache consistency maintenance algorithms for mobile computing environments: stateless and stateful. In a stateless approach, the server is unaware of the cache contents at a mobile user (MU). Even though stateless approaches employ simple database management schemes, they lack scalability and ability to support user disconnectedness and mobility. On the other hand, a stateful approach is scalable for large database systems at the cost of nontrivial overhead due to server database management. We propose a novel algorithm, called Scalable Asynchronous Cache Consistency Scheme (SACCS), which inherits the positive features of both stateless and stateful approaches. SACCS provides a weak cache consistency for unreliable communication (e.g., wireless mobile) environments with small stale cache hit probability. It is also a highly scalable algorithm with minimum database management overhead. The properties are accomplished through the use of flag bits at the server cache (SC) and MU cache (MUC), an identifier (ID) in MUC for each entry after its invalidation, and estimated time-to-live (TTL) for each cached entry, as well as rendering of all valid entries of MUC to uncertain state when an MU wakes up. The stale cache hit probability is analyzed and also simulated under the Rayleigh fading model of error-prone wireless channels. Comprehensive simulation results show that the performance of SACCS is superior to those of other existing stateful and stateless algorithms in both single and multicell mobile environments.     

Buffer management in a real-time shared disks cluster

A great deal of research indicates that the shared disks (SD) cluster is suitable to high performance transaction processing. However, the aggregation of SD cluster with real-time processing has not been investigated. By adopting cluster technology, the real-time services will be highly available and can exploit internode parallelism. In this paper, we consider buffer management issues in a real-time SD cluster. We first propose a real-time buffer coherency algorithm that exploits inherent characteristics of real-time applications and SD cluster. Then we extend traditional buffer replacement algorithms to the real-time SD cluster. They emphasize specific attributes of buffer pages to capitalize locality of references, transaction deadline, and affinity-based routing. We evaluate the performance of the proposed algorithms under a wide variety of transaction workloads and system configurations.     

无线传感器节点低功耗的研究

为了最大限度地延长传感器节点的生存时间,电路、结构、算法和协议必须满足能量有效性.就单个传感器节点角度来看,可以节省能耗的方法有很多,其中动态功率管理(DPM)和动态电压调节(DVS)是两种有效节省CPU能耗的方法.在三星S3C2410芯片上测试,改变处理器的频率,验证了功耗和频率的线性关系.通过仿真分析了CPU能耗与缓冲器长度的关系,说明了缓冲器溢出概率对CPU功耗的影响关系,得出在DVS的基础上增加缓冲器长度或降低溢出概率可以进一步节省能耗.     

Quantitative cross impact analysis with latent semantic indexing

Cross impact analysis (CIA) consists of a set of related methodologies that predict the occurrence probability of a specific event and that also predict the conditional probability of a first event given a second event. The conditional probability can be interpreted as the impact of the second event on the first. Most of the CIA methodologies are qualitative that means the occurrence and conditional probabilities are calculated based on estimations of human experts. In recent years, an increased number of quantitative methodologies can be seen that use a large number of data from databases and the internet. Nearly 80% of all data available in the internet are textual information and thus, knowledge structure based approaches on textual information for calculating the conditional probabilities are proposed in literature. In contrast to related methodologies, this work proposes a new quantitative CIA methodology to predict the conditional probability based on the semantic structure of given textual information. Latent semantic indexing is used to identify the hidden semantic patterns standing behind an event and to calculate the impact of the patterns on other semantic textual patterns representing a different event. This enables to calculate the conditional probabilities semantically. A case study shows that this semantic approach can be used to predict the conditional probability of a technology on a different technology.     

资源调度等待开销感知的虚拟机整合

近年来,数据中心庞大的能源开销问题引起广泛关注.虚拟化管理平台可以通过虚拟机迁移技术将虚拟机整合到更少的服务器上,从而提高数据中心能源有效性.对面向数据中心节能的虚拟机整合研究工作进行调研,并总结虚拟机整合研究存在的3个挑战.针对已有工作未考虑虚拟机等待资源调度带来的服务器资源额外开销这种现象,开展了资源调度等待开销感知的虚拟机整合研究.从理论和实验上证明了在具有实际意义的约束条件下,存在着虚拟机等待资源调度带来的服务器资源额外开销,且随着整合虚拟机数量的增长保持稳定.基于典型工作负载的实验结果表明,这个额外开销平均占据了11.7%的服务器资源开销.此外,提出了资源预留整合（MRC）算法,用于改进已有的虚拟机整合算法.算法模拟实验结果表明,MRC算法相比于常用的虚拟机整合算法FFD（first fit decreasing）,明显降低了服务器资源溢出概率.     

Managing Multiuser Database Buffers Using Data Mining Techniques

In this paper, we propose a data-mining-based approach to public buffer management for a multiuser database system, where database buffers are organized into two areas – public and private. While the private buffer areas contain pages to be updated by particular users, the public buffer area contains pages shared among different users. Unlike traditional buffer management strategies where limited knowledge of user access patterns is used, the proposed approach discovers knowledge from page access sequences of user transactions and uses it to guide public buffer placement and replacement. A prefetch strategy is exploited based on the discovered page access knowledge. In practice, to make such a data-mining-based buffer management approach tractable, we present a soft variation to approximate our absolute best buffer replacement solution. The knowledge to be discovered and the discovery methods are discussed in the paper. The effectiveness of the proposed approach was investigated through a simulation study. The results indicate that with the help of the discovered knowledge, the public buffer hit ratio can be improved significantly, while the added computational complexity, compared to the achievement in buffer hit ratio, is less. In some situations, the time cost of the data-mining-based buffer management policy is even lower than that of the simplest buffer management policy.     

基于ARC的闪存数据库缓冲区算法

闪存是一种纯电子设备,具备体积小、数据读取速度快、能耗低、抗震性强等优点,被用来部分替代机械硬盘从而提升存储系统的性能.但是,现有的缓冲区置换算法都是针对机械硬盘的物理特性进行设计和优化,因此有必要针对闪存的物理特性重新设计缓冲区置换算法.提出一种新的面向闪存数据库的缓冲区替换算法CF-ARC.算法设计了一种新的页替换机制,即在替换干净页或者脏页的时候考虑其访问频度的大小,优先将访问频度少的干净页替换出缓冲区,使得热页继续留在缓冲区提高命中率,从而获得更好的性能,通过对实验结果的对比分析发现CF-ARC在多数情况下具有比其它置换算法更高的性能.     

Runtime data center temperature prediction using Grammatical Evolution techniques

Data Centers are huge power consumers, both because of the energy required for computation and the cooling needed to keep servers below thermal redlining. The most common technique to minimize cooling costs is increasing data room temperature. However, to avoid reliability issues, and to enhance energy efficiency, there is a need to predict the temperature attained by servers under variable cooling setups. Due to the complex thermal dynamics of data rooms, accurate runtime data center temperature prediction has remained as an important challenge. By using Grammatical Evolution techniques, this paper presents a methodology for the generation of temperature models for data centers and the runtime prediction of CPU and inlet temperature under variable cooling setups. As opposed to time costly Computational Fluid Dynamics techniques, our models do not need specific knowledge about the problem, can be used in arbitrary data centers, re-trained if conditions change and have negligible overhead during runtime prediction. Our models have been trained and tested by using traces from real Data Center scenarios. Our results show how we can fully predict the temperature of the servers in a data rooms, with prediction errors below 2 °C and 0.5 °C in CPU and server inlet temperature respectively.     

HAT: an efficient buffer management method for flash-based hybrid storage systems

Flash solid-state drives (SSDs) provide much faster access to data compared with traditional hard disk drives (HDDs). The current price and performance of SSD suggest it can be adopted as a data buffer between main memory and HDD, and buffer management policy in such hybrid systems has attracted more and more interest from research community recently. In this paper, we propose a novel approach to manage the buffer in flash-based hybrid storage systems, named hotness aware hit (HAT). HAT exploits a page reference queue to record the access history as well as the status of accessed pages, i.e., hot, warm, and cold. Additionally, the page reference queue is further split into hot and warm regions which correspond to the memory and flash in general. The HAT approach updates the page status and deals with the page migration in the memory hierarchy according to the current page status and hit position in the page reference queue. Compared with the existing hybrid storage approaches, the proposed HAT can manage the memory and flash cache layers more effectively. Our empirical evaluation on benchmark traces demonstrates the superiority of the proposed strategy against the state-of-the-art competitors.     

A trace-driven simulation study of dynamic load balancing

A trace-driven simulation study of dynamic load balancing in homogeneous distributed systems supporting broadcasting is presented. Information about job CPU and input/output (I/O) demands collected from production systems is used as input to a simulation model that includes a representative CPU scheduling policy and considers the message exchange and job transfer cost explicitly. Seven load-balancing algorithms are simulated and their performances compared. Load balancing is capable of significantly reducing the mean and standard deviation of job response times, especially under heavy load, and for jobs with high resource demands. Algorithms based on periodic or nonperiodic load information exchange provide similar performance, and, among the periodic policies, the algorithms that use a distinguished agent to collect and distribute load information cut down the overhead and scale better. With initial job placements only, source initiative algorithms were found to perform better than server initiative algorithms. The performances of all hosts, even those originally with light loads, are generally improved by load balancing