Asma Charfi, C. Mraidha, S. Gérard, F. Terrier, Pierre Boulet
This paper addresses the problem of code optimization for Real-Time and Embedded Systems (RTES). Such systems are designed using Model-Based Development (MBD)approach that consists of performing three major steps: building models, generating code from them and compiling the generated code. Actually, during the code generation, an important part of the modeling language semantics which could be useful for optimization is lost, thus, making impossible some optimizations achievement. This paper shows how adding a new level of optimization at the model level results in a more compact code. It also discusses the impact of the code generation on optimization: whether this step promotes or prevents optimizations. We conclude on a proposal of a new MBD approach containing only steps that advance optimization: modeling and compiling steps.
{"title":"Does Code Generation Promote or Prevent Optimizations?","authors":"Asma Charfi, C. Mraidha, S. Gérard, F. Terrier, Pierre Boulet","doi":"10.1109/ISORC.2010.25","DOIUrl":"https://doi.org/10.1109/ISORC.2010.25","url":null,"abstract":"This paper addresses the problem of code optimization for Real-Time and Embedded Systems (RTES). Such systems are designed using Model-Based Development (MBD)approach that consists of performing three major steps: building models, generating code from them and compiling the generated code. Actually, during the code generation, an important part of the modeling language semantics which could be useful for optimization is lost, thus, making impossible some optimizations achievement. This paper shows how adding a new level of optimization at the model level results in a more compact code. It also discusses the impact of the code generation on optimization: whether this step promotes or prevents optimizations. We conclude on a proposal of a new MBD approach containing only steps that advance optimization: modeling and compiling steps.","PeriodicalId":142767,"journal":{"name":"2010 13th IEEE International Symposium on Object/Component/Service-Oriented Real-Time Distributed Computing","volume":"166 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-05-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131579224","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}
Julian Wolf, M. Gerdes, Florian Kluge, S. Uhrig, Jörg Mische, Stefan Metzlaff, Christine Rochange, H. Cassé, P. Sainrat, T. Ungerer
Multi-cores are the contemporary solution to satisfy high performance and low energy demands in general and embedded computing domains. However, currently available multi-cores are not feasible to be used in safety-critical environments with hard real-time constraints. Hard real-time tasks running on different cores must be executed in isolation or their interferences must be time-bounded. Thus, new requirements also arise for a real-time operating system (RTOS), in particular if the parallel execution of hard real-time applications should be supported. In this paper we focus on the MERASA system software as an RTOS developed on top of the MERASA multi-core processor. The MERASA system software fulfils the requirements for time-bounded execution of parallel hard real-time tasks. In particular we focus on thread control with synchronisation mechanisms, memory management and resource management requirements. Our evaluations show that all system software functions are time-bounded by a worst-case execution time (WCET) analysis.
{"title":"RTOS Support for Parallel Execution of Hard Real-Time Applications on the MERASA Multi-core Processor","authors":"Julian Wolf, M. Gerdes, Florian Kluge, S. Uhrig, Jörg Mische, Stefan Metzlaff, Christine Rochange, H. Cassé, P. Sainrat, T. Ungerer","doi":"10.1109/ISORC.2010.31","DOIUrl":"https://doi.org/10.1109/ISORC.2010.31","url":null,"abstract":"Multi-cores are the contemporary solution to satisfy high performance and low energy demands in general and embedded computing domains. However, currently available multi-cores are not feasible to be used in safety-critical environments with hard real-time constraints. Hard real-time tasks running on different cores must be executed in isolation or their interferences must be time-bounded. Thus, new requirements also arise for a real-time operating system (RTOS), in particular if the parallel execution of hard real-time applications should be supported. In this paper we focus on the MERASA system software as an RTOS developed on top of the MERASA multi-core processor. The MERASA system software fulfils the requirements for time-bounded execution of parallel hard real-time tasks. In particular we focus on thread control with synchronisation mechanisms, memory management and resource management requirements. Our evaluations show that all system software functions are time-bounded by a worst-case execution time (WCET) analysis.","PeriodicalId":142767,"journal":{"name":"2010 13th IEEE International Symposium on Object/Component/Service-Oriented Real-Time Distributed Computing","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-05-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125370198","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}
James H. Hill, H. Sutherland, Paul Stodinger, Thomas Silveria, D. Schmidt, J. M. Slaby, N. Visnevski
Performance analysis tools for enterprise distributed real-time and embedded (DRE) systems require instrumenting heterogeneous sources (such as application- and system-level hardware and software resources). Traditional techniques for software instrumentation of such systems, however, are tightly coupled to system design and metrics of interest. It is therefore hard for system testers to increase their knowledge base and analytical capabilities for enterprise DRE system performance using existing instrumentation techniques when metrics of interest are not known during initial system design. This paper provides two contributions to research on software instrumentation for enterprise DRE systems. First, it presents OASIS, which is service-oriented middleware for instrumenting enterprise DRE systems to collect and extract metrics without design time knowledge of which metrics are collected. Second, this paper empirically evaluates OASIS in the context of a representative enterprise DRE system from the domain of shipboard computing. Results from applying OASIS to a representative enterprise DRE system show that its flexibility enables DRE system testers to precisely control the overhead incurred via instrumentation.
{"title":"OASIS: A Service-Oriented Architecture for Dynamic Instrumentation of Enterprise Distributed Real-Time and Embedded Systems","authors":"James H. Hill, H. Sutherland, Paul Stodinger, Thomas Silveria, D. Schmidt, J. M. Slaby, N. Visnevski","doi":"10.1109/ISORC.2010.29","DOIUrl":"https://doi.org/10.1109/ISORC.2010.29","url":null,"abstract":"Performance analysis tools for enterprise distributed real-time and embedded (DRE) systems require instrumenting heterogeneous sources (such as application- and system-level hardware and software resources). Traditional techniques for software instrumentation of such systems, however, are tightly coupled to system design and metrics of interest. It is therefore hard for system testers to increase their knowledge base and analytical capabilities for enterprise DRE system performance using existing instrumentation techniques when metrics of interest are not known during initial system design. This paper provides two contributions to research on software instrumentation for enterprise DRE systems. First, it presents OASIS, which is service-oriented middleware for instrumenting enterprise DRE systems to collect and extract metrics without design time knowledge of which metrics are collected. Second, this paper empirically evaluates OASIS in the context of a representative enterprise DRE system from the domain of shipboard computing. Results from applying OASIS to a representative enterprise DRE system show that its flexibility enables DRE system testers to precisely control the overhead incurred via instrumentation.","PeriodicalId":142767,"journal":{"name":"2010 13th IEEE International Symposium on Object/Component/Service-Oriented Real-Time Distributed Computing","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-05-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122605464","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}
Divide-and-conquer approaches to worst-case execution-time analysis (WCET analysis) pose a safety risk when applied to code for complex modern processors: Interferences between the hardware acceleration mechanisms of these processors lead to timing anomalies, i.e., a local timing change causes an either larger or inverse change of the global timing. This phenomenon may result in dangerous WCET underestimation. This paper presents intermediate results of our work on strategies for eliminating timing anomalies. These strategies are purely based on the modification of software, i.e., they do not require any changes to hardware. In an effort to eliminate the timing anomalies originating from the processor’s out-of-order instruction pipeline, we explored different methods of inserting instructions in the program code that render the dynamic instruction scheduler inoperative. We explain how the proposed strategies remove the timing anomalies caused by the pipeline. In the absence of working solutions for timing analysis for these complex processors, we chose portable metrics from compiler construction to assess the properties of our algorithms.
{"title":"Avoiding Timing Anomalies Using Code Transformations","authors":"Albrecht Kadlec, R. Kirner, P. Puschner","doi":"10.1109/ISORC.2010.27","DOIUrl":"https://doi.org/10.1109/ISORC.2010.27","url":null,"abstract":"Divide-and-conquer approaches to worst-case execution-time analysis (WCET analysis) pose a safety risk when applied to code for complex modern processors: Interferences between the hardware acceleration mechanisms of these processors lead to timing anomalies, i.e., a local timing change causes an either larger or inverse change of the global timing. This phenomenon may result in dangerous WCET underestimation. This paper presents intermediate results of our work on strategies for eliminating timing anomalies. These strategies are purely based on the modification of software, i.e., they do not require any changes to hardware. In an effort to eliminate the timing anomalies originating from the processor’s out-of-order instruction pipeline, we explored different methods of inserting instructions in the program code that render the dynamic instruction scheduler inoperative. We explain how the proposed strategies remove the timing anomalies caused by the pipeline. In the absence of working solutions for timing analysis for these complex processors, we chose portable metrics from compiler construction to assess the properties of our algorithms.","PeriodicalId":142767,"journal":{"name":"2010 13th IEEE International Symposium on Object/Component/Service-Oriented Real-Time Distributed Computing","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-05-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122536782","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}
This paper proposes a different approach for service adaptation which aims to: (i) support non-regular adaptation; (ii) integrate adaptation and model checking. First, a pushdown automaton is used to model the adaptor so that non-regular languages are possible. Second, behavior interfaces of services are modeled by B¨uchi automata in order to take the advantage of the acceptance condition. By defining the property of ”behavior mismatch free” in a LTL formula using acceptance condition, the detection of behavior mismatches is performed by model checking. Also, the adaptor generation is performed by model checking of pushdown systems with the guidance of a special over-behavioral adaptor called “coordinator”. Then the returned counterexample is converted to a pushdown automaton, the expected adaptor.
{"title":"Non-regular Adaptation of Services Using Model Checking","authors":"Hsin-hung Lin, Toshiaki Aoki, T. Katayama","doi":"10.1109/ISORC.2010.30","DOIUrl":"https://doi.org/10.1109/ISORC.2010.30","url":null,"abstract":"This paper proposes a different approach for service adaptation which aims to: (i) support non-regular adaptation; (ii) integrate adaptation and model checking. First, a pushdown automaton is used to model the adaptor so that non-regular languages are possible. Second, behavior interfaces of services are modeled by B¨uchi automata in order to take the advantage of the acceptance condition. By defining the property of ”behavior mismatch free” in a LTL formula using acceptance condition, the detection of behavior mismatches is performed by model checking. Also, the adaptor generation is performed by model checking of pushdown systems with the guidance of a special over-behavioral adaptor called “coordinator”. Then the returned counterexample is converted to a pushdown automaton, the expected adaptor.","PeriodicalId":142767,"journal":{"name":"2010 13th IEEE International Symposium on Object/Component/Service-Oriented Real-Time Distributed Computing","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-05-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126629609","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}
Juan Pedro Silva, M. D. Miguel, Javier Fernández Briones, A. Alonso
Applying model-driven development methodologies provide inherent benefits such as increased productivity, greater reuse, and better maintainability, to name a few. Efforts on achieving model-driven development of web services already exist. However, there is currently no complete solution that addresses non-functional aspects of these services as well. This paper presents an ongoing work which seeks to integrate these non-functional aspects in the development of web services, with a clear emphasis on security.
{"title":"Model-Driven Development of a Web Service-Oriented Architecture and Security Policies","authors":"Juan Pedro Silva, M. D. Miguel, Javier Fernández Briones, A. Alonso","doi":"10.1109/ISORC.2010.34","DOIUrl":"https://doi.org/10.1109/ISORC.2010.34","url":null,"abstract":"Applying model-driven development methodologies provide inherent benefits such as increased productivity, greater reuse, and better maintainability, to name a few. Efforts on achieving model-driven development of web services already exist. However, there is currently no complete solution that addresses non-functional aspects of these services as well. This paper presents an ongoing work which seeks to integrate these non-functional aspects in the development of web services, with a clear emphasis on security.","PeriodicalId":142767,"journal":{"name":"2010 13th IEEE International Symposium on Object/Component/Service-Oriented Real-Time Distributed Computing","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-05-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130799938","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}
Power consumption, performance and reliability are the most important parameters in modern safety-critical distributed real-time embedded systems. This paper evaluates and compares different schedulability conditions in fault-tolerant Rate-Monotonic (RM) and Earliest-Deadline-First (EDF) algorithms, with respect to their power efficiency. The primary-backup scheme is used to implement fault tolerance in the algorithms. To evaluate the algorithms, a software tool is developed that can simulate an embedded system consisting of n processors and m periodic tasks. The results show that depending on the different schedulability conditions, the EDF algorithm implemented with the Best-Fit policy is on average 9.6% more power efficient than other algorithms when n=1500 and m=1000. between the two selected schedulability conditions in the RM algorithm, the Utilization Oriented (UO) condition implemented with the Best-Fit policy is on average 5% more power efficient than the other schedulability condition.
{"title":"Investigating the Effects of Schedulability Conditions on the Power Efficiency of Task Scheduling in an Embedded System","authors":"M. Bashiri, S. Miremadi","doi":"10.1109/ISORC.2010.24","DOIUrl":"https://doi.org/10.1109/ISORC.2010.24","url":null,"abstract":"Power consumption, performance and reliability are the most important parameters in modern safety-critical distributed real-time embedded systems. This paper evaluates and compares different schedulability conditions in fault-tolerant Rate-Monotonic (RM) and Earliest-Deadline-First (EDF) algorithms, with respect to their power efficiency. The primary-backup scheme is used to implement fault tolerance in the algorithms. To evaluate the algorithms, a software tool is developed that can simulate an embedded system consisting of n processors and m periodic tasks. The results show that depending on the different schedulability conditions, the EDF algorithm implemented with the Best-Fit policy is on average 9.6% more power efficient than other algorithms when n=1500 and m=1000. between the two selected schedulability conditions in the RM algorithm, the Utilization Oriented (UO) condition implemented with the Best-Fit policy is on average 5% more power efficient than the other schedulability condition.","PeriodicalId":142767,"journal":{"name":"2010 13th IEEE International Symposium on Object/Component/Service-Oriented Real-Time Distributed Computing","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-05-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128066176","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}
The development of distributed real-time control-systems that must satisfy a certain set of timing constraints with an ever-increasing functionality leads to a considerable complexity growth. Tackling the complexity challenge and providing a consistent notion of time are key challenges, on which this research work is focused. The proposed Executable Time-Triggered Model (E-TTM) provides a deterministic (time and value domain) executable modeling approach for the composable development of distributed real-time control-systems. E-TTM provides a consistent notion of time and supports different strategies to tackle the complexity challenge such as abstraction, partition and segmentation. E-TTM metamodel has been implemented as a C++ library that extends SystemC with the time-triggered Model of Computation (MoC). This approach is illustrated with a case study.
{"title":"Executable Time-Triggered Model (E-TTM) for Real-Time Control Systems","authors":"Jon Perez, Antonio Perez, R. Obermaisser","doi":"10.1109/ISORC.2010.40","DOIUrl":"https://doi.org/10.1109/ISORC.2010.40","url":null,"abstract":"The development of distributed real-time control-systems that must satisfy a certain set of timing constraints with an ever-increasing functionality leads to a considerable complexity growth. Tackling the complexity challenge and providing a consistent notion of time are key challenges, on which this research work is focused. The proposed Executable Time-Triggered Model (E-TTM) provides a deterministic (time and value domain) executable modeling approach for the composable development of distributed real-time control-systems. E-TTM provides a consistent notion of time and supports different strategies to tackle the complexity challenge such as abstraction, partition and segmentation. E-TTM metamodel has been implemented as a C++ library that extends SystemC with the time-triggered Model of Computation (MoC). This approach is illustrated with a case study.","PeriodicalId":142767,"journal":{"name":"2010 13th IEEE International Symposium on Object/Component/Service-Oriented Real-Time Distributed Computing","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-05-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117286423","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}
Many real-time systems use preemptive priorities in their internals to guarantee certain real-time performance. This includes technologies that range from RTSJ (The Real-Time Specification for Java) to middleware like Real-Time CORBA (Common Object Request Broker Architecture) which offers additional models and policies that blend client and server information. This decision makes easier the integration of real-time acceptance tests and dispatching policies in these kinds of infrastructures. In this paper, we analyze different tradeoffs that emerge from the definition of different propagation models for distributed real-time Java. The paper covers technological integration aspects, impact on interfaces, and other practical issues more related to the performance that this model offers to a real-time application
{"title":"Towards Propagation of Non-functional Information in Distributed Real-Time Java","authors":"P. Basanta-Val, M. García-Valls, I. Estévez-Ayres","doi":"10.1109/ISORC.2010.28","DOIUrl":"https://doi.org/10.1109/ISORC.2010.28","url":null,"abstract":"Many real-time systems use preemptive priorities in their internals to guarantee certain real-time performance. This includes technologies that range from RTSJ (The Real-Time Specification for Java) to middleware like Real-Time CORBA (Common Object Request Broker Architecture) which offers additional models and policies that blend client and server information. This decision makes easier the integration of real-time acceptance tests and dispatching policies in these kinds of infrastructures. In this paper, we analyze different tradeoffs that emerge from the definition of different propagation models for distributed real-time Java. The paper covers technological integration aspects, impact on interfaces, and other practical issues more related to the performance that this model offers to a real-time application","PeriodicalId":142767,"journal":{"name":"2010 13th IEEE International Symposium on Object/Component/Service-Oriented Real-Time Distributed Computing","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-05-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130324625","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}
Nan Li, Hong Li, Jian Wu, Xiaofeng Zhong, Zheng Sun, Wei Bao
Creating GUI can be a time and money consuming work in application development. In AUTOSAR methodology for automotive electronics software development, configuration GUI with a large number of configuration items is required in the ECU (Electronic Control Unit) configuration step. To reduce the development time and cost, and meet the requirement of future update of AUTOSAR standard, we present a way for automatic GUI generation of AUTOSAR ECU configuration tool. Our approach adds the configuration information to class models in form of annotations and binds the configuration type and attributes information with configuration values implicitly. Based on the annotated models, the Configuration GUI can be generated. With the approach, our ECU configuration tool has been developed with great enhancement of efficiency, scalability and upgradeability.
{"title":"AUTOSAR Based Automatic GUI Generation","authors":"Nan Li, Hong Li, Jian Wu, Xiaofeng Zhong, Zheng Sun, Wei Bao","doi":"10.1109/ISORC.2010.35","DOIUrl":"https://doi.org/10.1109/ISORC.2010.35","url":null,"abstract":"Creating GUI can be a time and money consuming work in application development. In AUTOSAR methodology for automotive electronics software development, configuration GUI with a large number of configuration items is required in the ECU (Electronic Control Unit) configuration step. To reduce the development time and cost, and meet the requirement of future update of AUTOSAR standard, we present a way for automatic GUI generation of AUTOSAR ECU configuration tool. Our approach adds the configuration information to class models in form of annotations and binds the configuration type and attributes information with configuration values implicitly. Based on the annotated models, the Configuration GUI can be generated. With the approach, our ECU configuration tool has been developed with great enhancement of efficiency, scalability and upgradeability.","PeriodicalId":142767,"journal":{"name":"2010 13th IEEE International Symposium on Object/Component/Service-Oriented Real-Time Distributed Computing","volume":"57 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-05-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123333436","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：