2002 Pacific Rim International Symposium on Dependable Computing, 2002. Proceedings.最新文献

{"title":"Consensus in synchronous systems: a concise guided tour","authors":"M. Raynal","doi":"10.1109/PRDC.2002.1185641","DOIUrl":"https://doi.org/10.1109/PRDC.2002.1185641","url":null,"abstract":"This paper considers consensus protocols for synchronous systems where processes can commit crash failures, omission failures or Byzantine failures. It presents and revisits consensus protocols coping with such failures in an increasing order of difficulty. The paper can be seen as a short tutorial whose aim is to make the reader familiar with synchrony assumptions, different definitions of the consensus problem, and a hierarchy of process failure models. An important concern of the paper lies in simplicity. In addition to the survey flavor of the paper, several results that are presented are new, among which the ones concerning the omission failure model.","PeriodicalId":362330,"journal":{"name":"2002 Pacific Rim International Symposium on Dependable Computing, 2002. Proceedings.","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126428545","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"An adaptive high-low water mark destage algorithm for cached RAID5","authors":"Y. Nam, Chanik Park","doi":"10.1109/PRDC.2002.1185636","DOIUrl":"https://doi.org/10.1109/PRDC.2002.1185636","url":null,"abstract":"The high-low water mark destage (HLWM) algorithm is widely used to enable a cached RAID5 to flush dirty data from its write cache to disks. It activates and deactivates a destaging process based on two time-invariant thresholds which are determined by cache occupancy levels. However the opportunity exists to improve I/O throughput by adaptively changing the thresholds. This paper proposes an adaptive HLWM algorithm which dynamically changes its thresholds according to a varying I/O workload. Two thresholds are defined as the multiplication of changing rates of the cache occupancy level and the time required to fill and empty the cache. Performance evaluations with a cached RAID5 simulator reveal that the proposed algorithm outperforms the HLWM algorithm in terms of read response time, write cache hit ratio, and disk utilization.","PeriodicalId":362330,"journal":{"name":"2002 Pacific Rim International Symposium on Dependable Computing, 2002. Proceedings.","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116838017","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Perspectives on dependable computing for solar system exploration","authors":"L. Alkalai","doi":"10.1109/PRDC.2002.1185634","DOIUrl":"https://doi.org/10.1109/PRDC.2002.1185634","url":null,"abstract":"This year marks the silver anniversary of the launch of the Voyager 1 and 2 spacecraft which are still operational after 25 years in outer space. As both spacecraft rush towards the outer limits of our solar system in search for the heliopause, their life-time seems to be limited by the on-board available power supply and not the spacecraft reliability. Since the launch of the Voyager spacecraft in 1977, NASA has engaged in an active solar system exploration scientific program that has reached almost every planet in our solar system. Moreover, this year, the US National Research Council (NRC) Space Studies Board published a report called “New Frontiers in Solar System Exploration – An Integrated Exploration Strategy” which provides a survey of solar system exploration knowledge and makes recommendations for future solar system exploration priorities and mission opportunities. In this talk, we provide a perspective on one enabling technology aspect of solar system exploration: Dependable Computing. Whereas we reflect on the engineering marvels of the Voyager and other past and present spacecraft, our focus is on the future of solar system exploration. In particular, we anticipate that solar system missions in the coming decade will increasingly involve aspects of: a) in-situ exploration (as in addition to remote sensing); b) advanced surface, sub-surface and aerial mobility elements such as planetary rovers, surface penetrators and probes, aerobots, etc.; and c) collecting and returning samples to Earth. These future mission concepts present a new engineering and technical challenge for dependable computing in space. Two aspects are particularly worth noting. First, innovative new power source capabilities may enable ultra-long life space exploration. Second, all destinations considered for in-situ exploration of the solar system involve some aspect of survivability in extreme environments. These conditions include extreme low-temperatures ranging from Mars, and further out to Jupiter, Europa, Titan, etc. However, suggested explorations of the Venus surface require survivability in extreme high-temperature environments. These conditions are further compounded by (in some cases extreme) radiation exposure as well as hostile atmosphere (including high pressure). The design of high-performance avionics for autonomous spacecraft control and survivability in extreme environments represents the major challenge for future dependable systems in space. Moreover, future in-situ mobility systems will benefit from the additional technology push towards systems miniaturization and low power. We will describe current on-going efforts for addressing some of these technical challenges for the future of solar system exploration.","PeriodicalId":362330,"journal":{"name":"2002 Pacific Rim International Symposium on Dependable Computing, 2002. Proceedings.","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129211923","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Reliability analysis of grid computing systems","authors":"Yuan-Shun Dai, M. Xie, K. Poh","doi":"10.1109/PRDC.2002.1185624","DOIUrl":"https://doi.org/10.1109/PRDC.2002.1185624","url":null,"abstract":"Grid computing system is different from conventional distributed computing systems by its focus on large-scale resource sharing, where processors and communication have significant influence on grid computing reliability. Most previous research on conventional small-scale distributed systems ignored the communication time and processing time when studying the distributed program reliability, which is not practical in the analysis of grid computing systems. This paper describes the property of the grid computing systems and presents algorithms to analyze the grid program and system reliability.","PeriodicalId":362330,"journal":{"name":"2002 Pacific Rim International Symposium on Dependable Computing, 2002. Proceedings.","volume":"80 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128422230","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Principles of multi-level reflection for fault tolerant architectures","authors":"François Taïani, J. Fabre, M. Killijian","doi":"10.1109/PRDC.2002.1185619","DOIUrl":"https://doi.org/10.1109/PRDC.2002.1185619","url":null,"abstract":"We present the principles of multi-level reflection as an enabling technology for the design and implementation of adaptive fault tolerant systems. By exhibiting the structural and behavioral aspects of a software component, the reflection paradigm enables the design and implementation of appropriate non-functional mechanisms at a meta-level. The separation of concerns provided by reflective architectures makes reflection a perfect match for fault tolerance mechanisms. However, in order to provide the necessary and sufficient information for error detection and recovery, reflection must be applied to all system layers in an orthogonal manner. This is the main motivation behind the notion of multi-level reflection that is introduced. We describe the basic concepts of this new architectural paradigm, and illustrate them with concrete examples. We also discuss some practical work that has recently been carried out to start implementing the proposed framework.","PeriodicalId":362330,"journal":{"name":"2002 Pacific Rim International Symposium on Dependable Computing, 2002. Proceedings.","volume":"314 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124852771","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Formal verification of a pipelined processor with new memory hierarchy using a commercial model checker","authors":"Hiroshi Nakamura, T. Arai, M. Fujita","doi":"10.1109/PRDC.2002.1185653","DOIUrl":"https://doi.org/10.1109/PRDC.2002.1185653","url":null,"abstract":"Recently, model checkers have become commercially available. To investigate their ability, Solidify is selected as the representative of them and applied to a verification of a new processor. The processor adopts new memory hierarchy and new instructions. Its instruction issue is pipelined and in-order. Our experiment reveals that Solidify can verify the processor but drastic abstraction is indispensable for successful verification. The experimental results also suggest that it is quite hard to verify more complex out-of-order issue processors without very drastic and efficient abstraction. Through the experience, we also recognize the benefit of fully automatic verification. However, we suffer from the invariant problems. Experience is still important for this problem.","PeriodicalId":362330,"journal":{"name":"2002 Pacific Rim International Symposium on Dependable Computing, 2002. Proceedings.","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122096638","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"An extreme value injection approach with reduced learning time to make MLNs multiple-weight-fault tolerant","authors":"I. Takanami, Y. Oyama","doi":"10.1109/PRDC.2002.1185650","DOIUrl":"https://doi.org/10.1109/PRDC.2002.1185650","url":null,"abstract":"We propose an efficient method for making multilayered neural networks(MLN) fault-tolerant to all multiple weight faults in an interval by injecting intentionally two extreme values in the interval in a learning phase. The degree of fault-tolerance to a multiple weight fault is measured by the number of essential multiple links. First, we analytically discuss how to choose effectively the multiple links to be injected, and present a learning algorithm for making MLNs fault tolerant to all multiple (i.e., simultaneous) faults in the interval defined by two multi-dimensional extreme points. Then it is shown that after the learning algorithm successfully finishes, MLNs become fault tolerant to all multiple faults in the interval. The time in a weight modification cycle is almost linear for the fault multiplicity. The simulation results show that the computing time drastically reduces as the multiplicity increases.","PeriodicalId":362330,"journal":{"name":"2002 Pacific Rim International Symposium on Dependable Computing, 2002. Proceedings.","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131353202","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A consensus algorithm for synchronous distributed systems using mobile agent","authors":"Jiannong Cao, Xianbing Wang, Siu Lo, Sajal K. Das","doi":"10.1109/PRDC.2002.1185642","DOIUrl":"https://doi.org/10.1109/PRDC.2002.1185642","url":null,"abstract":"In this paper, we present a consensus algorithm for synchronous distributed systems using cooperating mobile agents. The algorithm is designed within a framework for mobile agent enabled distributed server groups (MADSG), where cooperating mobile agents are used to achieve coordination among the servers. Being autonomous and cooperative, cooperating mobile agents exchange information among themselves to achieve consensus. The correctness proof of the proposed algorithm is presented. Performance evaluation of the algorithm has been carried out by both theoretical analysis and simulation.","PeriodicalId":362330,"journal":{"name":"2002 Pacific Rim International Symposium on Dependable Computing, 2002. Proceedings.","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134619500","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Analyzing network reliability with imperfect nodes using OBDD","authors":"Fu-Min Yeh, Hung-Yau Lin, S. Kuo","doi":"10.1109/PRDC.2002.1185623","DOIUrl":"https://doi.org/10.1109/PRDC.2002.1185623","url":null,"abstract":"The nodes as well as the links may fail in a real network. Almost all the existing tree-based partitioning algorithms are inefficient in finding the disjoint paths in a large network even if all the nodes are perfect. The number of disjoint paths will increase dramatically if a network has imperfect nodes. In this paper, strategies based on edge expansion diagram using OBDD are proposed to efficiently evaluate the reliability of a network with imperfect nodes. The fixed sink algorithm is proposed to further speed up the process for k-terminal networks. The essential variable is also defined to help us identify the most critical part of the network. Our methods are better than previous numeric algorithms and have two significant results. First, it takes only about 65 seconds to identify the essential variable for a 2/sup 99/-path network on a SPARC 20 with 128 MB of memory. Second, the overhead due to considering imperfect nodes is as low as 0.2% in average for seven st3/spl times/n networks, where n = 13, 14,..., 19.","PeriodicalId":362330,"journal":{"name":"2002 Pacific Rim International Symposium on Dependable Computing, 2002. Proceedings.","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128950037","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Providing persistence for sensor streams with light neighbor WAL","authors":"H. Kawashima, Motomichi Toyama, Y. Anzai, M. Imai","doi":"10.1109/PRDC.2002.1185645","DOIUrl":"https://doi.org/10.1109/PRDC.2002.1185645","url":null,"abstract":"Sensor database systems need to provide both freshness of data and persistence to the incoming sensor streams. To provide persistence, a disk based logging method has been widely used, however it is not applicable for sensor streams because of its tardiness. In this paper, we propose the light neighbor write ahead logging protocol(L-WAL) for sensor streams. The L-WAL is a refinement of the neighbor-WAL (N-WAL). The L-WAL needs two network interfaces and applies a relaxed protocol rather than a two phase commit protocol. Since the relaxed protocol weakens the guarantee of logging successes, we have incorporated a repair system and checker system to enhance the guarantee. The result of experiments shows that the L-WAL is about 2.13 times faster than the N-WAL when the number of concurrent sensor streams is 250 and the L-WAL can enhance the persistence of data almost for free, while the N-WAL needs to pay high cost.","PeriodicalId":362330,"journal":{"name":"2002 Pacific Rim International Symposium on Dependable Computing, 2002. Proceedings.","volume":"76 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115517768","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}