Xiaoqi Chen, Shir Landau Feibish, Yaron Koral, J. Rexford, Ori Rottenstreich
Short-lived traffic surges, known as microbursts, can cause periods of unexpectedly high packet delay and loss on a link. Today, preventing microbursts requires deploying switches with larger packet buffers (incurring higher cost) or running the network at low utilization (sacrificing efficiency). Instead, we argue that switches should detect microbursts as they form, and take corrective action before the situation gets worse. This requires an efficient way for switches to identify the particular flows responsible for a microburst, and handle them automatically (e.g., by pacing, marking, or rerouting the packets). However, collecting fine-grained statistics about queue occupancy in real time is challenging, even with emerging programmable data planes. We present Snappy, which identifies the flows responsible for a microburst in real time. Snappy maintains multiple snapshots of the occupants of the queue over time, where each snapshot is a compact data structure that makes eicient use of data-plane memory. As each new packet arrives, Snappy updates one snapshot and also estimates the fraction of the queue occupied by the associated flow. Our simulations with data-center packet traces show that Snappy can target the flows responsible for microbursts at the sub-millisecond level.
{"title":"Catching the Microburst Culprits with Snappy","authors":"Xiaoqi Chen, Shir Landau Feibish, Yaron Koral, J. Rexford, Ori Rottenstreich","doi":"10.1145/3229584.3229586","DOIUrl":"https://doi.org/10.1145/3229584.3229586","url":null,"abstract":"Short-lived traffic surges, known as microbursts, can cause periods of unexpectedly high packet delay and loss on a link. Today, preventing microbursts requires deploying switches with larger packet buffers (incurring higher cost) or running the network at low utilization (sacrificing efficiency). Instead, we argue that switches should detect microbursts as they form, and take corrective action before the situation gets worse. This requires an efficient way for switches to identify the particular flows responsible for a microburst, and handle them automatically (e.g., by pacing, marking, or rerouting the packets). However, collecting fine-grained statistics about queue occupancy in real time is challenging, even with emerging programmable data planes. We present Snappy, which identifies the flows responsible for a microburst in real time. Snappy maintains multiple snapshots of the occupants of the queue over time, where each snapshot is a compact data structure that makes eicient use of data-plane memory. As each new packet arrives, Snappy updates one snapshot and also estimates the fraction of the queue occupied by the associated flow. Our simulations with data-center packet traces show that Snappy can target the flows responsible for microbursts at the sub-millisecond level.","PeriodicalId":326661,"journal":{"name":"Proceedings of the Afternoon Workshop on Self-Driving Networks","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2018-08-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115171133","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}
H. Liu, Xin Wu, Wei Zhou, Wei-ye Chen, Tao Wang, Hui Xu, Lei Zhou, Qing Ma, Ming Zhang
Managing the life cycle of network configurations, including the generation, update, transition and diagnosis of the configurations, is the primary task of network operators and a critical process for the reliability and efficiency of the networks. This paper presents NetCraft, a framework which automates the life cycle management of network configurations with a unified network model. Designed for life cycle automation, NetCraft's network model can expressively encode all parts and protocols in the network; It can be converted to or constructed from configurations with interoperability; It is able to perform fine-grained configurations with flexibility to deactivate or undo any configurations for safe configuration updates; And it can work without cooperations from device vendors. We have built and deployed an initial version of NetCraft in Alibaba's global WAN. Evaluations in real environments show that NetCraft can reduce the network incidents caused by configurations by 95% and cut the average time to plan and execute a network update by up to 93%.
{"title":"Automatic Life Cycle Management of Network Configurations","authors":"H. Liu, Xin Wu, Wei Zhou, Wei-ye Chen, Tao Wang, Hui Xu, Lei Zhou, Qing Ma, Ming Zhang","doi":"10.1145/3229584.3229585","DOIUrl":"https://doi.org/10.1145/3229584.3229585","url":null,"abstract":"Managing the life cycle of network configurations, including the generation, update, transition and diagnosis of the configurations, is the primary task of network operators and a critical process for the reliability and efficiency of the networks. This paper presents NetCraft, a framework which automates the life cycle management of network configurations with a unified network model. Designed for life cycle automation, NetCraft's network model can expressively encode all parts and protocols in the network; It can be converted to or constructed from configurations with interoperability; It is able to perform fine-grained configurations with flexibility to deactivate or undo any configurations for safe configuration updates; And it can work without cooperations from device vendors. We have built and deployed an initial version of NetCraft in Alibaba's global WAN. Evaluations in real environments show that NetCraft can reduce the network incidents caused by configurations by 95% and cut the average time to plan and execute a network update by up to 93%.","PeriodicalId":326661,"journal":{"name":"Proceedings of the Afternoon Workshop on Self-Driving Networks","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2018-08-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120879740","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}
Henri Maxime Demoulin, Isaac Pedisich, L. T. Phan, B. T. Loo
This paper presents a novel integrated platform for the automatic detection and mitigation of denial-of-service (DoS) attacks in networked systems. Recently, these attacks have evolved from simple flooding at the network layer to targeted, application-specific asymmetric attacks. Because of this trend, existing techniques---which rely primarily on network classification at the edge or core routing devices---are becoming ineffective. Our platform integrates machine learning with fine-grained application-level performance metrics and monitoring statistics at the software's components to achieve precise traffic classification for detecting application-specific attacks in real time. When an attack is detected, the platform will then automatically isolate suspicious traffic by routing it to separate component instances with a fixed resource reservation, thus preventing it from interfering with the rest of the system. Our evaluation using a range of asymmetric attacks shows that our detection technique is highly effective and that the close-loop integration of real-time detection and traffic isolation can deliver substantially better quality-of-service for good users in the presence of attacks than the default mitigation using dynamic scaling of resource alone.
{"title":"Automated Detection and Mitigation of Application-level Asymmetric DoS Attacks","authors":"Henri Maxime Demoulin, Isaac Pedisich, L. T. Phan, B. T. Loo","doi":"10.1145/3229584.3229589","DOIUrl":"https://doi.org/10.1145/3229584.3229589","url":null,"abstract":"This paper presents a novel integrated platform for the automatic detection and mitigation of denial-of-service (DoS) attacks in networked systems. Recently, these attacks have evolved from simple flooding at the network layer to targeted, application-specific asymmetric attacks. Because of this trend, existing techniques---which rely primarily on network classification at the edge or core routing devices---are becoming ineffective. Our platform integrates machine learning with fine-grained application-level performance metrics and monitoring statistics at the software's components to achieve precise traffic classification for detecting application-specific attacks in real time. When an attack is detected, the platform will then automatically isolate suspicious traffic by routing it to separate component instances with a fixed resource reservation, thus preventing it from interfering with the rest of the system. Our evaluation using a range of asymmetric attacks shows that our detection technique is highly effective and that the close-loop integration of real-time detection and traffic isolation can deliver substantially better quality-of-service for good users in the presence of attacks than the default mitigation using dynamic scaling of resource alone.","PeriodicalId":326661,"journal":{"name":"Proceedings of the Afternoon Workshop on Self-Driving Networks","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2018-08-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124570809","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}
A. Jacobs, R. Pfitscher, R. Ferreira, L. Granville
Recent advances in artificial intelligence (AI) offer an opportunity for the adoption of self-driving networks. However, network operators or home-network users still do not have the right tools to exploit these new advancements in AI, since they have to rely on low-level languages to specify network policies. Intent-based networking (IBN) allows operators to specify high-level policies that dictate how the network should behave without worrying how they are translated into configuration commands in the network devices. However, the existing research proposals for IBN fail to exploit the knowledge and feedback of the network operator to validate or improve the translation of intents. In this paper, we introduce a novel intent-refinement process that uses machine learning and feedback from the operator to translate the operator's utterances into network configurations. Our refinement process uses a sequence-to-sequence learning model to extract intents from natural language and the feedback from the operator to improve learning. The key insight of our process is an intermediate representation that resembles natural language that is suitable to collect feedback from the operator but is structured enough to facilitate precise translations. Our prototype interacts with a network operator using natural language and translates the operator input to the intermediate representation before translating to SDN rules. Our experimental results show that our process achieves a correlation coefficient squared (i.e., R-squared) of 0.99 for a dataset with 5000 entries and the operator feedback significantly improves the accuracy of our model.
{"title":"Refining Network Intents for Self-Driving Networks","authors":"A. Jacobs, R. Pfitscher, R. Ferreira, L. Granville","doi":"10.1145/3229584.3229590","DOIUrl":"https://doi.org/10.1145/3229584.3229590","url":null,"abstract":"Recent advances in artificial intelligence (AI) offer an opportunity for the adoption of self-driving networks. However, network operators or home-network users still do not have the right tools to exploit these new advancements in AI, since they have to rely on low-level languages to specify network policies. Intent-based networking (IBN) allows operators to specify high-level policies that dictate how the network should behave without worrying how they are translated into configuration commands in the network devices. However, the existing research proposals for IBN fail to exploit the knowledge and feedback of the network operator to validate or improve the translation of intents. In this paper, we introduce a novel intent-refinement process that uses machine learning and feedback from the operator to translate the operator's utterances into network configurations. Our refinement process uses a sequence-to-sequence learning model to extract intents from natural language and the feedback from the operator to improve learning. The key insight of our process is an intermediate representation that resembles natural language that is suitable to collect feedback from the operator but is structured enough to facilitate precise translations. Our prototype interacts with a network operator using natural language and translates the operator input to the intermediate representation before translating to SDN rules. Our experimental results show that our process achieves a correlation coefficient squared (i.e., R-squared) of 0.99 for a dataset with 5000 entries and the operator feedback significantly improves the accuracy of our model.","PeriodicalId":326661,"journal":{"name":"Proceedings of the Afternoon Workshop on Self-Driving Networks","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2018-08-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117262752","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}
Patrick Kalmbach, Johannes Zerwas, P. Babarczi, Andreas Blenk, W. Kellerer, S. Schmid
As emerging network technologies and softwareization render networks more flexible, the question arises of how to exploit these flexibilities for optimization. Given the complexity of the involved network protocols and the context in which networks are operating, such optimizations are increasingly difficult to perform. An interesting vision in this regard are "self-driving" networks: networks which measure, analyze and control themselves in an automated manner, reacting to changes in the environment (e.g., demand), while exploiting existing flexibilities to optimize themselves. A fundamental challenge faced by any (self-)optimizing network concerns the limited knowledge about future changes in the demand and environment in which the network is operating. Indeed, given that reconfigurations entail resource costs and may take time, an "optimal" network configuration for the current demand and environment may not necessarily be optimal also in the near future. Thus, it is desirable that (self-)optimizations also prepare the network for possibly unexpected events. This paper makes the case for empowering self-driving networks: empowerment is an information-centric measure which accounts for how "prepared" a network is and how much flexibility is preserved over time. While empowerment has been successfully employed in other domains such as robotics, we are not aware of any applications in networking. As a case study for the use of empowerment in networks, we consider self-driving networks offering topological flexibilities, i.e., reconfigurable edges.
{"title":"Empowering Self-Driving Networks","authors":"Patrick Kalmbach, Johannes Zerwas, P. Babarczi, Andreas Blenk, W. Kellerer, S. Schmid","doi":"10.1145/3229584.3229587","DOIUrl":"https://doi.org/10.1145/3229584.3229587","url":null,"abstract":"As emerging network technologies and softwareization render networks more flexible, the question arises of how to exploit these flexibilities for optimization. Given the complexity of the involved network protocols and the context in which networks are operating, such optimizations are increasingly difficult to perform. An interesting vision in this regard are \"self-driving\" networks: networks which measure, analyze and control themselves in an automated manner, reacting to changes in the environment (e.g., demand), while exploiting existing flexibilities to optimize themselves. A fundamental challenge faced by any (self-)optimizing network concerns the limited knowledge about future changes in the demand and environment in which the network is operating. Indeed, given that reconfigurations entail resource costs and may take time, an \"optimal\" network configuration for the current demand and environment may not necessarily be optimal also in the near future. Thus, it is desirable that (self-)optimizations also prepare the network for possibly unexpected events. This paper makes the case for empowering self-driving networks: empowerment is an information-centric measure which accounts for how \"prepared\" a network is and how much flexibility is preserved over time. While empowerment has been successfully employed in other domains such as robotics, we are not aware of any applications in networking. As a case study for the use of empowerment in networks, we consider self-driving networks offering topological flexibilities, i.e., reconfigurable edges.","PeriodicalId":326661,"journal":{"name":"Proceedings of the Afternoon Workshop on Self-Driving Networks","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2018-08-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115744688","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":"Proceedings of the Afternoon Workshop on Self-Driving Networks","authors":"","doi":"10.1145/3229584","DOIUrl":"https://doi.org/10.1145/3229584","url":null,"abstract":"","PeriodicalId":326661,"journal":{"name":"Proceedings of the Afternoon Workshop on Self-Driving Networks","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2018-08-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129088167","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}
Touseef Yaqoob, M. Usama, Junaid Qadir, Gareth Tyson
Along with recent networking advances (such as software-defined networks, network functions virtualization, and programmable data planes), the networking field, in a bid to construct highly optimized self-driving and self-organizing networks, is increasingly embracing artificial intelligence and machine learning. It is worth remembering that the modern Internet that interconnects millions of networks is a 'complex adaptive social system', in which interventions not only cause effects but the effects have further knock-on consequences (not all of which are desirable or anticipated). We believe that self-driving networks will likely raise new unanticipated challenges (particularly in the human-facing domains of ethics, privacy, and security). In this paper, we propose the use of insights and tools from the field of "systems thinking"---a rich discipline developing for more than half a century, which encompasses more realistic models of complex social systems---and highlight their relevance for studying the long-term effects of network architectural interventions, particularly for self-driving networks. We show that these tools complement existing simulation and modeling tools and provide new insights and capabilities. To the best of our knowledge, this is the first study that has considered the relevance of formal systems thinking tools for the analysis of self-driving networks.
{"title":"On Analyzing Self-Driving Networks: A Systems Thinking Approach","authors":"Touseef Yaqoob, M. Usama, Junaid Qadir, Gareth Tyson","doi":"10.1145/3229584.3229588","DOIUrl":"https://doi.org/10.1145/3229584.3229588","url":null,"abstract":"Along with recent networking advances (such as software-defined networks, network functions virtualization, and programmable data planes), the networking field, in a bid to construct highly optimized self-driving and self-organizing networks, is increasingly embracing artificial intelligence and machine learning. It is worth remembering that the modern Internet that interconnects millions of networks is a 'complex adaptive social system', in which interventions not only cause effects but the effects have further knock-on consequences (not all of which are desirable or anticipated). We believe that self-driving networks will likely raise new unanticipated challenges (particularly in the human-facing domains of ethics, privacy, and security). In this paper, we propose the use of insights and tools from the field of \"systems thinking\"---a rich discipline developing for more than half a century, which encompasses more realistic models of complex social systems---and highlight their relevance for studying the long-term effects of network architectural interventions, particularly for self-driving networks. We show that these tools complement existing simulation and modeling tools and provide new insights and capabilities. To the best of our knowledge, this is the first study that has considered the relevance of formal systems thinking tools for the analysis of self-driving networks.","PeriodicalId":326661,"journal":{"name":"Proceedings of the Afternoon Workshop on Self-Driving Networks","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2018-04-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134387984","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：