Pub Date : 1999-02-10DOI: 10.1109/PCCC.1999.749461
A. Iselt
Redundant transmission on disjoint paths is a common precaution against the effects of failures in communication networks. To allow hitless switching from one path to the other, synchronization algorithms are required. Most of the current algorithms are based on supplementary synchronization information (e.g. synchronization cells). A novel algorithm for the synchronization and selection of redundant data streams is proposed, which allows hitless switching without supplementary information. The algorithm achieves synchronization based on the correlation of the user information. Further, it provides a fast synchronization detection time and is tolerant against loss and errors of single cells in one data path. Analytical analysis as well as simulation show the correctness and efficiency of the novel algorithm.
{"title":"A new synchronization algorithm for hitless protection switching in ATM networks","authors":"A. Iselt","doi":"10.1109/PCCC.1999.749461","DOIUrl":"https://doi.org/10.1109/PCCC.1999.749461","url":null,"abstract":"Redundant transmission on disjoint paths is a common precaution against the effects of failures in communication networks. To allow hitless switching from one path to the other, synchronization algorithms are required. Most of the current algorithms are based on supplementary synchronization information (e.g. synchronization cells). A novel algorithm for the synchronization and selection of redundant data streams is proposed, which allows hitless switching without supplementary information. The algorithm achieves synchronization based on the correlation of the user information. Further, it provides a fast synchronization detection time and is tolerant against loss and errors of single cells in one data path. Analytical analysis as well as simulation show the correctness and efficiency of the novel algorithm.","PeriodicalId":211210,"journal":{"name":"1999 IEEE International Performance, Computing and Communications Conference (Cat. No.99CH36305)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"1999-02-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124818147","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 : 1999-02-10DOI: 10.1109/PCCC.1999.749459
Xiaojun Shen, Fan Yang, Yi Pan
Since optical networks must support crosstalk-free (CF) connections, regular N/spl times/N multistage interconnection networks (MINs) cannot be directly used to provide connections between N inputs and N outputs. A solution is to use a 2N/spl times/2N Cube-Type MIN to provide the N/spl times/N connections. C. Qiao (1993) proposed a time domain approach that divides the N optical inputs into several groups such that CF connections can be provided by an N/spl times/N regular MIN in several time slots, one for each group. The set of N-permutations realizable in two slots is defined as class /spl theta/. Qiao proved that the size of /spl theta/ is larger than the size of class /spl Omega/, where /spl Omega/ consists of all N-permutations passible through a regular N/spl times/N Omega network. The paper first presents an optimal O(NlgN) time algorithm for identifying whether a given permutation belongs to class /spl theta/ or not. From this algorithm, the paper proves an interesting fact that the class /spl theta/ is identical to the class /spl Omega/+1 which represents the set of N-permutations admissible by a non-optical N/spl times/N one-extra stage Omega network.
{"title":"Equivalent permutation capabilities between time division optical omega network and non-optical extra stage omega network","authors":"Xiaojun Shen, Fan Yang, Yi Pan","doi":"10.1109/PCCC.1999.749459","DOIUrl":"https://doi.org/10.1109/PCCC.1999.749459","url":null,"abstract":"Since optical networks must support crosstalk-free (CF) connections, regular N/spl times/N multistage interconnection networks (MINs) cannot be directly used to provide connections between N inputs and N outputs. A solution is to use a 2N/spl times/2N Cube-Type MIN to provide the N/spl times/N connections. C. Qiao (1993) proposed a time domain approach that divides the N optical inputs into several groups such that CF connections can be provided by an N/spl times/N regular MIN in several time slots, one for each group. The set of N-permutations realizable in two slots is defined as class /spl theta/. Qiao proved that the size of /spl theta/ is larger than the size of class /spl Omega/, where /spl Omega/ consists of all N-permutations passible through a regular N/spl times/N Omega network. The paper first presents an optimal O(NlgN) time algorithm for identifying whether a given permutation belongs to class /spl theta/ or not. From this algorithm, the paper proves an interesting fact that the class /spl theta/ is identical to the class /spl Omega/+1 which represents the set of N-permutations admissible by a non-optical N/spl times/N one-extra stage Omega network.","PeriodicalId":211210,"journal":{"name":"1999 IEEE International Performance, Computing and Communications Conference (Cat. No.99CH36305)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"1999-02-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126823281","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 : 1999-02-10DOI: 10.1109/PCCC.1999.749435
A. Raghavendra, R. Kinicki
This paper presents results from a series of simulation experiments designed to study network performance when TCP Vegas and the Random Early Detection (RED) algorithm are used together. Using the x-Sim network simulator, simulation tests were conducted with a variety of traffic scenarios using both TCP Reno and TCP Vegas in combination with First-Come-First-Served (FCFS) and RED routers. Analysis of the performance results for three configurations shows that TCP Vegas host-dominated configurations perform better than TCP Reno host-dominated configurations and that the RED algorithm provides better fairness than FCFS. The RED improvement is higher when the configuration includes a mix of Reno and Vegas hosts. Furthermore, when the buffer allocation in a FCFS router is inadequate, the router performance becomes unstable under heavy traffic. When fragile and robust TCP sources send traffic into a congested router, the TCP Vegas/RED router combination provides the highest throughput and best fairness for the fragile hosts.
{"title":"A simulation performance study of TCP Vegas and Random Early Detection","authors":"A. Raghavendra, R. Kinicki","doi":"10.1109/PCCC.1999.749435","DOIUrl":"https://doi.org/10.1109/PCCC.1999.749435","url":null,"abstract":"This paper presents results from a series of simulation experiments designed to study network performance when TCP Vegas and the Random Early Detection (RED) algorithm are used together. Using the x-Sim network simulator, simulation tests were conducted with a variety of traffic scenarios using both TCP Reno and TCP Vegas in combination with First-Come-First-Served (FCFS) and RED routers. Analysis of the performance results for three configurations shows that TCP Vegas host-dominated configurations perform better than TCP Reno host-dominated configurations and that the RED algorithm provides better fairness than FCFS. The RED improvement is higher when the configuration includes a mix of Reno and Vegas hosts. Furthermore, when the buffer allocation in a FCFS router is inadequate, the router performance becomes unstable under heavy traffic. When fragile and robust TCP sources send traffic into a congested router, the TCP Vegas/RED router combination provides the highest throughput and best fairness for the fragile hosts.","PeriodicalId":211210,"journal":{"name":"1999 IEEE International Performance, Computing and Communications Conference (Cat. No.99CH36305)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"1999-02-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128423817","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 : 1999-02-10DOI: 10.1109/PCCC.1999.749442
S. Cooper, T. Bowman, A. Karshmer
This paper discusses a methodology for lifting a sessions trace from a packet trace. The session trace is created from a packet trace by removing many of the physical and network layer control mechanisms from the packet trace. The session trace embodies the true client/server transaction induced on the network link. We show that the session trace is superior to a packet trace for network simulation workloads in Network Simulator.
{"title":"Session traces: an enhancement to network simulator","authors":"S. Cooper, T. Bowman, A. Karshmer","doi":"10.1109/PCCC.1999.749442","DOIUrl":"https://doi.org/10.1109/PCCC.1999.749442","url":null,"abstract":"This paper discusses a methodology for lifting a sessions trace from a packet trace. The session trace is created from a packet trace by removing many of the physical and network layer control mechanisms from the packet trace. The session trace embodies the true client/server transaction induced on the network link. We show that the session trace is superior to a packet trace for network simulation workloads in Network Simulator.","PeriodicalId":211210,"journal":{"name":"1999 IEEE International Performance, Computing and Communications Conference (Cat. No.99CH36305)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"1999-02-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130787302","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 : 1999-02-10DOI: 10.1109/PCCC.1999.749424
C. B. Ahmed, N. Boudriga, M. Obaidat
An intelligent network (IN) is characterized by the distribution of network intelligence and capabilities wherever required within the telecommunications network. IN is also an architectural concept that can be applied to a variety of telecommunication networks including the public switched networks, mobile networks, and the integrated services digital networks (ISDNs). In this paper, we analyze and evaluate the performance of wireless ATM network equipped with intelligent services. The mathematical analysis uses the concept of virtual resource, while the simulation uses the object-oriented (O-O) scheme.
{"title":"Performance analysis of intelligent mobile ATM networks","authors":"C. B. Ahmed, N. Boudriga, M. Obaidat","doi":"10.1109/PCCC.1999.749424","DOIUrl":"https://doi.org/10.1109/PCCC.1999.749424","url":null,"abstract":"An intelligent network (IN) is characterized by the distribution of network intelligence and capabilities wherever required within the telecommunications network. IN is also an architectural concept that can be applied to a variety of telecommunication networks including the public switched networks, mobile networks, and the integrated services digital networks (ISDNs). In this paper, we analyze and evaluate the performance of wireless ATM network equipped with intelligent services. The mathematical analysis uses the concept of virtual resource, while the simulation uses the object-oriented (O-O) scheme.","PeriodicalId":211210,"journal":{"name":"1999 IEEE International Performance, Computing and Communications Conference (Cat. No.99CH36305)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"1999-02-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126567756","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 : 1999-02-10DOI: 10.1109/PCCC.1999.749447
Yimin Hu, Ashwini K. Nanda, Qing Yang
Performance of Web servers is critical to the success of many corporations and organizations. However, very few results have been published that quantitatively study the server behavior and identify the performance bottlenecks. In this paper we measured and analyzed the behavior of the popular Apache Web server on a uniprocessor system and a 4-CPU SMP (Symmetric Multi-Processor) system running the IBM AIX operating system. Using the AIX built-in tracing facility, we obtained detailed information on kernel events and system activities while running Apache driven by the SPECweb96 and the WebStone benchmarks. After quantitatively identifying the performance bottlenecks, we proposed and implemented 6 techniques that improve the throughput of Apache by 61%. These techniques are general purpose and can be applied to other Web servers as well.
Web服务器的性能对许多公司和组织的成功至关重要。然而，很少有人发表定量研究服务器行为和确定性能瓶颈的结果。在本文中，我们测量并分析了流行的Apache Web服务器在一个单处理器系统和一个运行IBM AIX操作系统的4 cpu SMP(对称多处理器)系统上的行为。使用AIX内置跟踪工具，我们获得了运行由SPECweb96和WebStone基准测试驱动的Apache时的内核事件和系统活动的详细信息。在定量地确定性能瓶颈之后，我们提出并实现了6项技术，这些技术将Apache的吞吐量提高了61%。这些技术是通用的，也可以应用于其他Web服务器。
{"title":"Measurement, analysis and performance improvement of the Apache Web server","authors":"Yimin Hu, Ashwini K. Nanda, Qing Yang","doi":"10.1109/PCCC.1999.749447","DOIUrl":"https://doi.org/10.1109/PCCC.1999.749447","url":null,"abstract":"Performance of Web servers is critical to the success of many corporations and organizations. However, very few results have been published that quantitatively study the server behavior and identify the performance bottlenecks. In this paper we measured and analyzed the behavior of the popular Apache Web server on a uniprocessor system and a 4-CPU SMP (Symmetric Multi-Processor) system running the IBM AIX operating system. Using the AIX built-in tracing facility, we obtained detailed information on kernel events and system activities while running Apache driven by the SPECweb96 and the WebStone benchmarks. After quantitatively identifying the performance bottlenecks, we proposed and implemented 6 techniques that improve the throughput of Apache by 61%. These techniques are general purpose and can be applied to other Web servers as well.","PeriodicalId":211210,"journal":{"name":"1999 IEEE International Performance, Computing and Communications Conference (Cat. No.99CH36305)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"1999-02-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115890682","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 : 1999-02-10DOI: 10.1109/PCCC.1999.749456
A. Iyengar
This paper describes a General-Purpose Software cache (GPS cache) which can improve the performance of many applications including Web servers and databases. It can service several hundred thousand cache hits per second on a uniprocessor. When used to cache data for a Web server accelerator, the overhead due to the GPS cache was an insignificant factor in the overall performance of the system. The GPS cache can store objects in memory, on disk, or both. The cache uses a new algorithm for managing expiration times of cached objects which is more efficient than previous ones. The GPS cache uses Data Update Propagation (DUP) to invalidate complex objects which is crucial for caching and maintaining updated copies of dynamic Web pages. Transactions can be logged using different buffering mechanisms in order to provide a balance between efficiency and currency of transaction log files. The GPS cache provides API functions which allow applications to directly manipulate its contents.
{"title":"Design and performance of a general-purpose software cache","authors":"A. Iyengar","doi":"10.1109/PCCC.1999.749456","DOIUrl":"https://doi.org/10.1109/PCCC.1999.749456","url":null,"abstract":"This paper describes a General-Purpose Software cache (GPS cache) which can improve the performance of many applications including Web servers and databases. It can service several hundred thousand cache hits per second on a uniprocessor. When used to cache data for a Web server accelerator, the overhead due to the GPS cache was an insignificant factor in the overall performance of the system. The GPS cache can store objects in memory, on disk, or both. The cache uses a new algorithm for managing expiration times of cached objects which is more efficient than previous ones. The GPS cache uses Data Update Propagation (DUP) to invalidate complex objects which is crucial for caching and maintaining updated copies of dynamic Web pages. Transactions can be logged using different buffering mechanisms in order to provide a balance between efficiency and currency of transaction log files. The GPS cache provides API functions which allow applications to directly manipulate its contents.","PeriodicalId":211210,"journal":{"name":"1999 IEEE International Performance, Computing and Communications Conference (Cat. No.99CH36305)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"1999-02-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121992648","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 : 1999-02-10DOI: 10.1109/PCCC.1999.749465
S. Bandyopadhyay, A. Jaekel, A. Sengupta
Commercially available fiber-optic cables allow limited numbers of wavelengths on a single fiber. In this paper we have developed a pragmatic method of implementing all-optical wavelength routed networks using bundles of fibers to realize each communication link. We have explored some interesting features of this approach for dynamic lightpath assignment. We have shown that our approach allows virtual wavelength translation where we may derive some benefits of partial wavelength translation without actually having to change the carrier frequency. This design also allows us to have bundles of varying sizes to accommodate anticipated differences in traffic through different communication links of the network. Finally, we have presented a simple dynamic scheme, based on local information alone, for allocating lightpaths.
{"title":"On a virtual wavelength translation scheme for routing in all-optical networks","authors":"S. Bandyopadhyay, A. Jaekel, A. Sengupta","doi":"10.1109/PCCC.1999.749465","DOIUrl":"https://doi.org/10.1109/PCCC.1999.749465","url":null,"abstract":"Commercially available fiber-optic cables allow limited numbers of wavelengths on a single fiber. In this paper we have developed a pragmatic method of implementing all-optical wavelength routed networks using bundles of fibers to realize each communication link. We have explored some interesting features of this approach for dynamic lightpath assignment. We have shown that our approach allows virtual wavelength translation where we may derive some benefits of partial wavelength translation without actually having to change the carrier frequency. This design also allows us to have bundles of varying sizes to accommodate anticipated differences in traffic through different communication links of the network. Finally, we have presented a simple dynamic scheme, based on local information alone, for allocating lightpaths.","PeriodicalId":211210,"journal":{"name":"1999 IEEE International Performance, Computing and Communications Conference (Cat. No.99CH36305)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"1999-02-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128170319","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 : 1999-02-10DOI: 10.1109/PCCC.1999.749471
M. Moudgill, P. Bose, J. Moreno
We describe the results in validating the performance projections from a parameterized trace-driven simulation model of a speculative out-of-order superscalar processor which has been developed with the objective of acting as a microarchitecture exploration tool. Because of its objective, the model-called Turandot-has been designed to deliver much higher simulation speed than what is achieved from detailed (RTL) processor models. We summarize the validation methodology used, and present experimental data gathered in the calibration of one processor organization modeled with Turandot against a detailed reference model. The results indicate that, on the average for SPECint95 sampled traces, Turandot is within 5% of the results reported by the reference model while exhibiting a speed-up factor of about 70.
{"title":"Validation of Turandot, a fast processor model for microarchitecture exploration","authors":"M. Moudgill, P. Bose, J. Moreno","doi":"10.1109/PCCC.1999.749471","DOIUrl":"https://doi.org/10.1109/PCCC.1999.749471","url":null,"abstract":"We describe the results in validating the performance projections from a parameterized trace-driven simulation model of a speculative out-of-order superscalar processor which has been developed with the objective of acting as a microarchitecture exploration tool. Because of its objective, the model-called Turandot-has been designed to deliver much higher simulation speed than what is achieved from detailed (RTL) processor models. We summarize the validation methodology used, and present experimental data gathered in the calibration of one processor organization modeled with Turandot against a detailed reference model. The results indicate that, on the average for SPECint95 sampled traces, Turandot is within 5% of the results reported by the reference model while exhibiting a speed-up factor of about 70.","PeriodicalId":211210,"journal":{"name":"1999 IEEE International Performance, Computing and Communications Conference (Cat. No.99CH36305)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"1999-02-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114612865","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 : 1999-02-10DOI: 10.1109/PCCC.1999.749457
S. Nettles
Comparative experimentation is increasingly important in computer science, but performing such experiments can be challenging. The paper presents a set of experiments that compare the performance of two persistent storage managers, and answer the question of whether the safer storage manager has performance comparable to the less safe one. This comparison was difficult for a number of reasons, among them: relatively few programs using either storage manager existed and no established benchmarks existed, and the two techniques are incompatible at the source code level, thus making a direct comparison impossible. In particular one storage manager used a malloc-and-free style of dynamic storage allocation, while the other used a high performance concurrent garbage collector. A number of approaches were used to overcome this difficulty. The most novel approach involved tracing the memory management of a production program that used the malloc-and-free based storage manager and then replaying the trace in an environment that allowed garbage collection and malloc-and-free to be compared. The study represents the most extensive study of a garbage collected persistent storage system to date.
{"title":"Sidney and RDS: an evaluation of two persistent storage systems","authors":"S. Nettles","doi":"10.1109/PCCC.1999.749457","DOIUrl":"https://doi.org/10.1109/PCCC.1999.749457","url":null,"abstract":"Comparative experimentation is increasingly important in computer science, but performing such experiments can be challenging. The paper presents a set of experiments that compare the performance of two persistent storage managers, and answer the question of whether the safer storage manager has performance comparable to the less safe one. This comparison was difficult for a number of reasons, among them: relatively few programs using either storage manager existed and no established benchmarks existed, and the two techniques are incompatible at the source code level, thus making a direct comparison impossible. In particular one storage manager used a malloc-and-free style of dynamic storage allocation, while the other used a high performance concurrent garbage collector. A number of approaches were used to overcome this difficulty. The most novel approach involved tracing the memory management of a production program that used the malloc-and-free based storage manager and then replaying the trace in an environment that allowed garbage collection and malloc-and-free to be compared. The study represents the most extensive study of a garbage collected persistent storage system to date.","PeriodicalId":211210,"journal":{"name":"1999 IEEE International Performance, Computing and Communications Conference (Cat. No.99CH36305)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"1999-02-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115422889","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：