Pub Date : 1998-12-14DOI: 10.1109/ICPADS.1998.741155
Chung-Ming Huang, Pei-Chuan Liu
Many networking applications become feasible and required with the popular use of Internet. We present an Interactive Digital Radio Station, which is called IDRS, over Internet. Several architecture and synchronization methods are proposed to solve the communication problems that only occur during the digital radio multicasting. In order to perform the communication between DJ and audience, two operation modes, which are called the DJ mode and the Call-in mode, are defined. Related technique issues and the corresponding system development are presented in detail.
{"title":"A multicast communication system over Internet and its application","authors":"Chung-Ming Huang, Pei-Chuan Liu","doi":"10.1109/ICPADS.1998.741155","DOIUrl":"https://doi.org/10.1109/ICPADS.1998.741155","url":null,"abstract":"Many networking applications become feasible and required with the popular use of Internet. We present an Interactive Digital Radio Station, which is called IDRS, over Internet. Several architecture and synchronization methods are proposed to solve the communication problems that only occur during the digital radio multicasting. In order to perform the communication between DJ and audience, two operation modes, which are called the DJ mode and the Call-in mode, are defined. Related technique issues and the corresponding system development are presented in detail.","PeriodicalId":226947,"journal":{"name":"Proceedings 1998 International Conference on Parallel and Distributed Systems (Cat. No.98TB100250)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"1998-12-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131305220","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}
Pub Date : 1998-12-14DOI: 10.1109/ICPADS.1998.741018
T. Chiueh, D. Margaritis, S. Varadarajan
Describes the design, implementation and evaluation of a parallel indexer called PAMIS (PArallel Multimedia Index Server) for a polygonal 2D shape image database. PAMIS is based on a shape representation scheme called the turning function, which exhibits the desirable properties of position, scale and rotation invariance, and has a similarity metric function that satisfies the triangular inequality, which is required for efficient database indexing. Because the goal of the PAMIS project is to support "like-this" image queries, the indexing scheme we chose, the vantage-point tree (VPT), uses relative rather than absolute distance values to organize the database elements for efficient nearest-neighbor searching. We have successfully implemented PAMIS on a network of workstations to exploit the I/O and computation parallelism inherent in the VPT algorithm. We found that it is preferable to make the VPT node size as small as possible in order to have a lean and deep VPT structure, and the best-case scheduling strategy performs the best among the scheduling strategies considered. Overall, the performance of the VPT algorithm scales very well with the number of processors, and the indexing efficiency (defined as the percentage of database elements touched by the search) of PAMIS is 6% and 39% for "good" queries that ask for 1 and 50 nearest neighbors, respectively.
{"title":"Design, implementation, and evaluation of a parallel index server for shape image database","authors":"T. Chiueh, D. Margaritis, S. Varadarajan","doi":"10.1109/ICPADS.1998.741018","DOIUrl":"https://doi.org/10.1109/ICPADS.1998.741018","url":null,"abstract":"Describes the design, implementation and evaluation of a parallel indexer called PAMIS (PArallel Multimedia Index Server) for a polygonal 2D shape image database. PAMIS is based on a shape representation scheme called the turning function, which exhibits the desirable properties of position, scale and rotation invariance, and has a similarity metric function that satisfies the triangular inequality, which is required for efficient database indexing. Because the goal of the PAMIS project is to support \"like-this\" image queries, the indexing scheme we chose, the vantage-point tree (VPT), uses relative rather than absolute distance values to organize the database elements for efficient nearest-neighbor searching. We have successfully implemented PAMIS on a network of workstations to exploit the I/O and computation parallelism inherent in the VPT algorithm. We found that it is preferable to make the VPT node size as small as possible in order to have a lean and deep VPT structure, and the best-case scheduling strategy performs the best among the scheduling strategies considered. Overall, the performance of the VPT algorithm scales very well with the number of processors, and the indexing efficiency (defined as the percentage of database elements touched by the search) of PAMIS is 6% and 39% for \"good\" queries that ask for 1 and 50 nearest neighbors, respectively.","PeriodicalId":226947,"journal":{"name":"Proceedings 1998 International Conference on Parallel and Distributed Systems (Cat. No.98TB100250)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"1998-12-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125683174","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}
Pub Date : 1998-12-14DOI: 10.1109/ICPADS.1998.741031
Yunjung Yi, T. Park, H. Yeom
This paper presents a causal logging scheme for the lazy release consistent distributed shared memory systems. Causal logging is a very attractive approach to provide fault tolerance for distributed systems, since it eliminates the need for stable logging. However since interprocess dependency must causally be transferred with the normal messages, the excessive message overhead has been a drawback of this approach. In order to achieve an efficient implementation of causal logging for distributed shared memory systems, the data structures and the operations supported by the lazy release consistency memory model are utilized. For example, to implement the sender-based logging of the message contents, the diff structure is utilized, and for the causal logging of the dependency information, the operations to support the causal propagation of the write notices are utilized. As a result, the causal logging for the lazy release consistent distributed shared memory system can be implemented with a very low overhead. The simulation results using parallel applications show only 1%-4.4% increases in the execution time.
{"title":"A causal logging scheme for lazy release consistent distributed shared memory systems","authors":"Yunjung Yi, T. Park, H. Yeom","doi":"10.1109/ICPADS.1998.741031","DOIUrl":"https://doi.org/10.1109/ICPADS.1998.741031","url":null,"abstract":"This paper presents a causal logging scheme for the lazy release consistent distributed shared memory systems. Causal logging is a very attractive approach to provide fault tolerance for distributed systems, since it eliminates the need for stable logging. However since interprocess dependency must causally be transferred with the normal messages, the excessive message overhead has been a drawback of this approach. In order to achieve an efficient implementation of causal logging for distributed shared memory systems, the data structures and the operations supported by the lazy release consistency memory model are utilized. For example, to implement the sender-based logging of the message contents, the diff structure is utilized, and for the causal logging of the dependency information, the operations to support the causal propagation of the write notices are utilized. As a result, the causal logging for the lazy release consistent distributed shared memory system can be implemented with a very low overhead. The simulation results using parallel applications show only 1%-4.4% increases in the execution time.","PeriodicalId":226947,"journal":{"name":"Proceedings 1998 International Conference on Parallel and Distributed Systems (Cat. No.98TB100250)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"1998-12-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123069462","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}
Pub Date : 1998-12-14DOI: 10.1109/ICPADS.1998.741158
C. Yeh, B. Parhami
In this paper, we propose a new presentation of graphs, called the index-permutation (IP) graph model, and apply it to the systematic development of communication-efficient interconnection networks. We derive several new classes of interconnection networks based on IP graphs to achieve the desired properties. We show that the diameters of some classes of IP graphs are optimal within a factor of 1+0(1) given their node degrees. Designs based on IP graphs can balance system resources by appropriately selecting network parameters, thus providing adaptability to future technology and application requirements.
{"title":"A new representation of graphs and its applications to parallel processing","authors":"C. Yeh, B. Parhami","doi":"10.1109/ICPADS.1998.741158","DOIUrl":"https://doi.org/10.1109/ICPADS.1998.741158","url":null,"abstract":"In this paper, we propose a new presentation of graphs, called the index-permutation (IP) graph model, and apply it to the systematic development of communication-efficient interconnection networks. We derive several new classes of interconnection networks based on IP graphs to achieve the desired properties. We show that the diameters of some classes of IP graphs are optimal within a factor of 1+0(1) given their node degrees. Designs based on IP graphs can balance system resources by appropriately selecting network parameters, thus providing adaptability to future technology and application requirements.","PeriodicalId":226947,"journal":{"name":"Proceedings 1998 International Conference on Parallel and Distributed Systems (Cat. No.98TB100250)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"1998-12-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130137032","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}
Pub Date : 1998-12-14DOI: 10.1109/ICPADS.1998.741040
M. Abdallah, R. Guerraoui, P. Pucheral
Although widely used in distributed transactional systems, the so-called Two-Phase Commit (2PC) protocol introduces a substantial delay in transaction processing, even in the absence of failures. This has led several researchers to look for alternative commit protocols that minimize the time cost associated with coordination messages and forced log writes in 2PC. In particular, variations of a One-Phase Commit (1PC) protocol have recently been proposed. Although efficient, 1PC is however rarely considered in practice because of the strong assumptions it requires from the distributed transactional system. The aim of the paper is to better identify and understand those assumptions. Through a careful look into the intrinsic characteristics of 1PC, we dissect the assumptions underlying it and we present simple techniques that minimize them. We believe that these techniques constitute a first step towards a serious reconsideration of 1PC in the transactional world.
{"title":"One-phase commit: does it make sense?","authors":"M. Abdallah, R. Guerraoui, P. Pucheral","doi":"10.1109/ICPADS.1998.741040","DOIUrl":"https://doi.org/10.1109/ICPADS.1998.741040","url":null,"abstract":"Although widely used in distributed transactional systems, the so-called Two-Phase Commit (2PC) protocol introduces a substantial delay in transaction processing, even in the absence of failures. This has led several researchers to look for alternative commit protocols that minimize the time cost associated with coordination messages and forced log writes in 2PC. In particular, variations of a One-Phase Commit (1PC) protocol have recently been proposed. Although efficient, 1PC is however rarely considered in practice because of the strong assumptions it requires from the distributed transactional system. The aim of the paper is to better identify and understand those assumptions. Through a careful look into the intrinsic characteristics of 1PC, we dissect the assumptions underlying it and we present simple techniques that minimize them. We believe that these techniques constitute a first step towards a serious reconsideration of 1PC in the transactional world.","PeriodicalId":226947,"journal":{"name":"Proceedings 1998 International Conference on Parallel and Distributed Systems (Cat. No.98TB100250)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"1998-12-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130895818","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}
Pub Date : 1998-12-14DOI: 10.1109/ICPADS.1998.741044
Gwang S. Jung, Q. Malluhi, W. G. Brown
The paper describes a scheme for high performance and dependable data storage and delivery in a large scale distributed computing and communication environment such as the Web environment. The proposed scheme utilizes the parallelism of several distributed data servers storing striped data blocks to achieve high throughput. It employs coding techniques to protect the system against data unavailability and hence achieve dependable service. The performance results show that the proposed method has several advantages over traditional ones, such as data service through mirror sites. The error probability of the proposed method is orders of magnitude smaller than that of the mirroring with the same redundancy rate. The data rates for file downloading could be improved significantly by the proposed scheme.
{"title":"A scheme for high-performance data delivery in the Web environment","authors":"Gwang S. Jung, Q. Malluhi, W. G. Brown","doi":"10.1109/ICPADS.1998.741044","DOIUrl":"https://doi.org/10.1109/ICPADS.1998.741044","url":null,"abstract":"The paper describes a scheme for high performance and dependable data storage and delivery in a large scale distributed computing and communication environment such as the Web environment. The proposed scheme utilizes the parallelism of several distributed data servers storing striped data blocks to achieve high throughput. It employs coding techniques to protect the system against data unavailability and hence achieve dependable service. The performance results show that the proposed method has several advantages over traditional ones, such as data service through mirror sites. The error probability of the proposed method is orders of magnitude smaller than that of the mirroring with the same redundancy rate. The data rates for file downloading could be improved significantly by the proposed scheme.","PeriodicalId":226947,"journal":{"name":"Proceedings 1998 International Conference on Parallel and Distributed Systems (Cat. No.98TB100250)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"1998-12-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130488076","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}
Pub Date : 1998-12-14DOI: 10.1109/ICPADS.1998.741164
Jang-sun Lee, Myungjoon Kim
The UPIO (User-controllable Parallel I/O) we proposed in (Lee et al., 1996) extends the abstraction of a linear file model into an n-dimensional file model and removes the limitations of the linear file model, allowing users to control the layout of data blocks across disks and aggregating disk bandwidth through UPIO's interfaces. This enables users to plan I/Os, computations, communications, and data reuse effectively in many scientific and engineering applications. These applications can be characterized by the corresponding stencil and implemented using stencil algorithms. We show how well UPIO produces high-performance external stencil codes by designing I/O and communication-efficient external Laplace equation solver algorithms and exploring the effects of UPIO with the codes.
我们在(Lee et al.， 1996)中提出的UPIO(用户可控并行I/O)将线性文件模型的抽象扩展为n维文件模型，并消除了线性文件模型的局限性，允许用户通过UPIO的接口控制磁盘上数据块的布局和聚合磁盘带宽。这使用户能够在许多科学和工程应用中有效地规划I/ o、计算、通信和数据重用。这些应用程序可以用相应的模板来表征，并使用模板算法来实现。我们通过设计I/O和通信高效的外部拉普拉斯方程求解算法，并探索UPIO对代码的影响，展示了UPIO如何很好地产生高性能的外部模板代码。
{"title":"High-performance external stencil computations using user-controllable I/O","authors":"Jang-sun Lee, Myungjoon Kim","doi":"10.1109/ICPADS.1998.741164","DOIUrl":"https://doi.org/10.1109/ICPADS.1998.741164","url":null,"abstract":"The UPIO (User-controllable Parallel I/O) we proposed in (Lee et al., 1996) extends the abstraction of a linear file model into an n-dimensional file model and removes the limitations of the linear file model, allowing users to control the layout of data blocks across disks and aggregating disk bandwidth through UPIO's interfaces. This enables users to plan I/Os, computations, communications, and data reuse effectively in many scientific and engineering applications. These applications can be characterized by the corresponding stencil and implemented using stencil algorithms. We show how well UPIO produces high-performance external stencil codes by designing I/O and communication-efficient external Laplace equation solver algorithms and exploring the effects of UPIO with the codes.","PeriodicalId":226947,"journal":{"name":"Proceedings 1998 International Conference on Parallel and Distributed Systems (Cat. No.98TB100250)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"1998-12-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131130255","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}
Pub Date : 1998-12-14DOI: 10.1109/ICPADS.1998.741171
Yan-Zou Liu, Su-Cheong Mac, C. Shieh
The main goal of parallel file subsystem on Distributed Shared Memory (DSM) systems is to reduce the network traffic in page based software DSM systems, thereby improving system performance. Our laboratory has built a prototype of the parallel file subsystem on two DSM systems, namely Cohesion and TreadMarks. But these two prototypes have several limitations: users must read/write the whole parallel file in a single access; users cannot modify an existing parallel file; the parallel file request must be issued from the root node. In our new parallel file subsystem on Teamster, a new DSM system developed by our laboratory, we eliminate the limitations revealed in the two previous parallel file subsystems. In addition, we have developed two new mechanisms, the software cache mechanism and the asynchronous file offset mechanism, to lessen the performance degradation caused by the frequent small accesses.
{"title":"Supporting small accesses for the parallel file subsystem on distributed shared memory systems","authors":"Yan-Zou Liu, Su-Cheong Mac, C. Shieh","doi":"10.1109/ICPADS.1998.741171","DOIUrl":"https://doi.org/10.1109/ICPADS.1998.741171","url":null,"abstract":"The main goal of parallel file subsystem on Distributed Shared Memory (DSM) systems is to reduce the network traffic in page based software DSM systems, thereby improving system performance. Our laboratory has built a prototype of the parallel file subsystem on two DSM systems, namely Cohesion and TreadMarks. But these two prototypes have several limitations: users must read/write the whole parallel file in a single access; users cannot modify an existing parallel file; the parallel file request must be issued from the root node. In our new parallel file subsystem on Teamster, a new DSM system developed by our laboratory, we eliminate the limitations revealed in the two previous parallel file subsystems. In addition, we have developed two new mechanisms, the software cache mechanism and the asynchronous file offset mechanism, to lessen the performance degradation caused by the frequent small accesses.","PeriodicalId":226947,"journal":{"name":"Proceedings 1998 International Conference on Parallel and Distributed Systems (Cat. No.98TB100250)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"1998-12-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133338049","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}
Pub Date : 1998-12-14DOI: 10.1109/ICPADS.1998.741021
SungHo Cho, K. Y. Bae, C. Hwang
The performance of optimistic concurrency control schemes is sensitive to the transaction abort rate. The abort probability can be reduced by reordering in order to reduce read-write conflicts. However, a potential drawback of reordering schemes is the space overhead in maintaining timestamps, multiple versions or a serialization graph. Furthermore, some transactions in optimistic concurrency control schemes may perform unnecessary operations even after the transactions have accessed write-write conflicting data items, because aborts happen only in the validation phase. In this paper, we propose a new broadcast scheme called BOCC-RS (Broadcast Optimistic Concurrency Control with Re-ordering Scheme) that can reduce the abort probability with low space overhead. In our scheme, the server maintains only one timestamp per data item for reordering. Moreover, our scheme reduces unnecessary operations. This paper presents a simulation study which shows that our scheme outperforms BOCC.
{"title":"A certification protocol with low space overhead","authors":"SungHo Cho, K. Y. Bae, C. Hwang","doi":"10.1109/ICPADS.1998.741021","DOIUrl":"https://doi.org/10.1109/ICPADS.1998.741021","url":null,"abstract":"The performance of optimistic concurrency control schemes is sensitive to the transaction abort rate. The abort probability can be reduced by reordering in order to reduce read-write conflicts. However, a potential drawback of reordering schemes is the space overhead in maintaining timestamps, multiple versions or a serialization graph. Furthermore, some transactions in optimistic concurrency control schemes may perform unnecessary operations even after the transactions have accessed write-write conflicting data items, because aborts happen only in the validation phase. In this paper, we propose a new broadcast scheme called BOCC-RS (Broadcast Optimistic Concurrency Control with Re-ordering Scheme) that can reduce the abort probability with low space overhead. In our scheme, the server maintains only one timestamp per data item for reordering. Moreover, our scheme reduces unnecessary operations. This paper presents a simulation study which shows that our scheme outperforms BOCC.","PeriodicalId":226947,"journal":{"name":"Proceedings 1998 International Conference on Parallel and Distributed Systems (Cat. No.98TB100250)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"1998-12-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114766681","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}
Pub Date : 1998-12-14DOI: 10.1109/ICPADS.1998.741132
Jau-Der Shih
In this paper, we present an adaptive fault-tolerant deadlock-free routing algorithm for torus networks by using four virtual channels. Messages are routed via shortest paths when there are no faults. When a message is blocked by a faulty block, the message will find a detour path to route around the faulty block. Based on the concept of unsafe nodes, we design a routing algorithm for tori that can tolerate block faults.
{"title":"Adaptive fault-tolerant wormhole routing for torus networks","authors":"Jau-Der Shih","doi":"10.1109/ICPADS.1998.741132","DOIUrl":"https://doi.org/10.1109/ICPADS.1998.741132","url":null,"abstract":"In this paper, we present an adaptive fault-tolerant deadlock-free routing algorithm for torus networks by using four virtual channels. Messages are routed via shortest paths when there are no faults. When a message is blocked by a faulty block, the message will find a detour path to route around the faulty block. Based on the concept of unsafe nodes, we design a routing algorithm for tori that can tolerate block faults.","PeriodicalId":226947,"journal":{"name":"Proceedings 1998 International Conference on Parallel and Distributed Systems (Cat. No.98TB100250)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"1998-12-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127660647","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：