Keqiang He, Junaid Khalid, Aaron Gember, Sourav Das, Chaithan Prakash, Aditya Akella, Erran L. Li, M. Thottan
Timely interaction between an SDN controller and switches is crucial to many SDN applications---e.g., fast rerouting during link failure and fine-grained traffic engineering in data centers. However, it is not well understood how the control plane in SDN switches impacts these applications. To this end, we conduct a comprehensive measurement study using four types of production SDN switches. Our measurements show that control actions, such as rule installation, have surprisingly high latency, due to both software implementation inefficiencies and fundamental traits of switch hardware.
{"title":"Measuring control plane latency in SDN-enabled switches","authors":"Keqiang He, Junaid Khalid, Aaron Gember, Sourav Das, Chaithan Prakash, Aditya Akella, Erran L. Li, M. Thottan","doi":"10.1145/2774993.2775069","DOIUrl":"https://doi.org/10.1145/2774993.2775069","url":null,"abstract":"Timely interaction between an SDN controller and switches is crucial to many SDN applications---e.g., fast rerouting during link failure and fine-grained traffic engineering in data centers. However, it is not well understood how the control plane in SDN switches impacts these applications. To this end, we conduct a comprehensive measurement study using four types of production SDN switches. Our measurements show that control actions, such as rule installation, have surprisingly high latency, due to both software implementation inefficiencies and fundamental traits of switch hardware.","PeriodicalId":316190,"journal":{"name":"Proceedings of the 1st ACM SIGCOMM Symposium on Software Defined Networking Research","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-06-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129863887","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}
Jeremie Miserez, Pavol Bielik, Ahmed El-Hassany, L. Vanbever, Martin T. Vechev
Software-Defined Networking (SDN) control software executes in highly asynchronous environments where unexpected concurrency errors can lead to performance or, worse, reachability errors. Unfortunately, detecting such errors is notoriously challenging, and SDN is no exception. Fundamentally, two ingredients are needed to build a concurrency analyzer: (i) a model of how different events are ordered, and (ii) the memory locations on which event accesses can interfere. In this paper we formulate the first happens-before (HB) model for SDNs enabling one to reason about ordering between events. We also present a commutativity specification of the network switch, allowing us to elegantly capture interference between concurrent events. Based on the above, we present the first dynamic concurrency analyzer for SDNs, called SdnRacer. SdnRacer uses the HB model and the commutativity rules to identify concurrency violations. Preliminary results indicate that the detector is practically effective---it can detect harmful violations quickly.
{"title":"SDNRacer: detecting concurrency violations in software-defined networks","authors":"Jeremie Miserez, Pavol Bielik, Ahmed El-Hassany, L. Vanbever, Martin T. Vechev","doi":"10.1145/2774993.2775004","DOIUrl":"https://doi.org/10.1145/2774993.2775004","url":null,"abstract":"Software-Defined Networking (SDN) control software executes in highly asynchronous environments where unexpected concurrency errors can lead to performance or, worse, reachability errors. Unfortunately, detecting such errors is notoriously challenging, and SDN is no exception. Fundamentally, two ingredients are needed to build a concurrency analyzer: (i) a model of how different events are ordered, and (ii) the memory locations on which event accesses can interfere. In this paper we formulate the first happens-before (HB) model for SDNs enabling one to reason about ordering between events. We also present a commutativity specification of the network switch, allowing us to elegantly capture interference between concurrent events. Based on the above, we present the first dynamic concurrency analyzer for SDNs, called SdnRacer. SdnRacer uses the HB model and the commutativity rules to identify concurrency violations. Preliminary results indicate that the detector is practically effective---it can detect harmful violations quickly.","PeriodicalId":316190,"journal":{"name":"Proceedings of the 1st ACM SIGCOMM Symposium on Software Defined Networking Research","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-06-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132214732","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}
In Software Defined Networks (SDN), users manage network services by abstracting high level service policies from lower level network functions. Edge-based SDN, which relies on end hosts to implement lower-level network functions, has been rapidly developed and widely adopted in cloud. A critical challenge in such an environment is to ensure that lower level network configurations, which are distributed in many end hosts, are in sync with high-level network service definitions, which are maintained in the central controller, as state inconsistency often arises in practice due to unreliable state dissemination, human errors, or software bugs. In this paper, we propose an approach to systematically extracting and analyzing the network states of OpenStack from both controller and end hosts, and identifying the inconsistencies between them across multiple network layers. Through extensive experiments, we demonstrate that our system can correctly identify network state inconsistencies with little system and network overhead, therefore can be adopted in large-scale production cloud to ensure healthy operations of its network services.
{"title":"Identifying SDN state inconsistency in OpenStack","authors":"Yang Xu, Yong Liu, Rahul Singh, S. Tao","doi":"10.1145/2774993.2775067","DOIUrl":"https://doi.org/10.1145/2774993.2775067","url":null,"abstract":"In Software Defined Networks (SDN), users manage network services by abstracting high level service policies from lower level network functions. Edge-based SDN, which relies on end hosts to implement lower-level network functions, has been rapidly developed and widely adopted in cloud. A critical challenge in such an environment is to ensure that lower level network configurations, which are distributed in many end hosts, are in sync with high-level network service definitions, which are maintained in the central controller, as state inconsistency often arises in practice due to unreliable state dissemination, human errors, or software bugs. In this paper, we propose an approach to systematically extracting and analyzing the network states of OpenStack from both controller and end hosts, and identifying the inconsistencies between them across multiple network layers. Through extensive experiments, we demonstrate that our system can correctly identify network state inconsistencies with little system and network overhead, therefore can be adopted in large-scale production cloud to ensure healthy operations of its network services.","PeriodicalId":316190,"journal":{"name":"Proceedings of the 1st ACM SIGCOMM Symposium on Software Defined Networking Research","volume":"65 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-06-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126463999","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 advancement of software-defined networking (SDN) technology is highly dependent on the successful transformations from in-house research ideas to real-life products. To enable such transformations, a testbed offering scalable and high fidelity networking environment for testing and evaluating new/existing designs is extremely valuable. Mininet, the most popular SDN emulator by far, is designed to achieve both accuracy and scalability by running unmodified code of network applications in lightweight Linux Containers. However, Mininet cannot guarantee performance fidelity under high workloads, in particular when the number of concurrent active events is more than the number of parallel cores. In this project, we develop a lightweight virtual time system in Linux container and integrate the system with Mininet, so that all the containers have their own virtual clocks rather than using the physical system clock which reflects the serialized execution of multiple containers. With the notion of virtual time, all the containers perceive virtual time as if they run independently and concurrently. As a result, interactions between the containers and the physical system are artificially scaled, making a network appear to be ten times faster from the viewpoint of applications within the containers than it actually is. We also design an adaptive virtual time scheduling subsystem in Mininet, which is responsible to balance the experiment speed and fidelity. Experimental results demonstrate that embedding virtual time into Mininet significantly enhances its performance fidelity, and therefore, results in a useful platform for the SDN community to conduct scalable experiments with high fidelity.
{"title":"VT-Mininet: Virtual-time-enabled Mininet for Scalable and Accurate Software-Define Network Emulation","authors":"Jiaqi Yan, Dong Jin","doi":"10.1145/2774993.2775012","DOIUrl":"https://doi.org/10.1145/2774993.2775012","url":null,"abstract":"The advancement of software-defined networking (SDN) technology is highly dependent on the successful transformations from in-house research ideas to real-life products. To enable such transformations, a testbed offering scalable and high fidelity networking environment for testing and evaluating new/existing designs is extremely valuable. Mininet, the most popular SDN emulator by far, is designed to achieve both accuracy and scalability by running unmodified code of network applications in lightweight Linux Containers. However, Mininet cannot guarantee performance fidelity under high workloads, in particular when the number of concurrent active events is more than the number of parallel cores. In this project, we develop a lightweight virtual time system in Linux container and integrate the system with Mininet, so that all the containers have their own virtual clocks rather than using the physical system clock which reflects the serialized execution of multiple containers. With the notion of virtual time, all the containers perceive virtual time as if they run independently and concurrently. As a result, interactions between the containers and the physical system are artificially scaled, making a network appear to be ten times faster from the viewpoint of applications within the containers than it actually is. We also design an adaptive virtual time scheduling subsystem in Mininet, which is responsible to balance the experiment speed and fidelity. Experimental results demonstrate that embedding virtual time into Mininet significantly enhances its performance fidelity, and therefore, results in a useful platform for the SDN community to conduct scalable experiments with high fidelity.","PeriodicalId":316190,"journal":{"name":"Proceedings of the 1st ACM SIGCOMM Symposium on Software Defined Networking Research","volume":"215 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-06-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115064692","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}
In recent years software network switches have regained eminence as a result of a number of growing trends, including the prominence of software-defined networks, as well as their use as back-ends to virtualization technologies, to name a few. Consequently, a number of high performance switches have been recently proposed in the literature, though none of these simultaneously provide (1) high packet rates, (2) high throughput, (3) low CPU usage, (4) high port density and (5) a flexible data plane. This is not by chance: these features conflict, and while achieving one or a few of them is (now) a solved problem, addressing the combination requires significant new design effort. In this paper we fill the gap by presenting mSwitch. To prove the flexibility and performance of our approach, we use mSwitch to build four distinct modules: a learning bridge consisting of 45 lines of code that outperforms FreeBSD's bridge by up to 8 times; an accelerated Open vSwitch module requiring small changes to the code and boosting performance by 2.6--3 times; a protocol demultiplexer for userspace protocol stacks; and a filtering module that can direct packets to virtualized middleboxes.
{"title":"mSwitch: a highly-scalable, modular software switch","authors":"Michio Honda, Felipe Huici, G. Lettieri, L. Rizzo","doi":"10.1145/2774993.2775065","DOIUrl":"https://doi.org/10.1145/2774993.2775065","url":null,"abstract":"In recent years software network switches have regained eminence as a result of a number of growing trends, including the prominence of software-defined networks, as well as their use as back-ends to virtualization technologies, to name a few. Consequently, a number of high performance switches have been recently proposed in the literature, though none of these simultaneously provide (1) high packet rates, (2) high throughput, (3) low CPU usage, (4) high port density and (5) a flexible data plane. This is not by chance: these features conflict, and while achieving one or a few of them is (now) a solved problem, addressing the combination requires significant new design effort. In this paper we fill the gap by presenting mSwitch. To prove the flexibility and performance of our approach, we use mSwitch to build four distinct modules: a learning bridge consisting of 45 lines of code that outperforms FreeBSD's bridge by up to 8 times; an accelerated Open vSwitch module requiring small changes to the code and boosting performance by 2.6--3 times; a protocol demultiplexer for userspace protocol stacks; and a filtering module that can direct packets to virtualized middleboxes.","PeriodicalId":316190,"journal":{"name":"Proceedings of the 1st ACM SIGCOMM Symposium on Software Defined Networking Research","volume":"70 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-06-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115706435","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}
Huynh Tu Dang, Daniele Sciascia, M. Canini, F. Pedone, R. Soulé
This paper explores the possibility of implementing the widely deployed Paxos consensus protocol in network devices. We present two different approaches: (i) a detailed design description for implementing the full Paxos logic in SDN switches, which identifies a sufficient set of required OpenFlow extensions; and (ii) an alternative, optimistic protocol which can be implemented without changes to the OpenFlow API, but relies on assumptions about how the network orders messages. Although neither of these protocols can be fully implemented without changes to the underlying switch firmware, we argue that such changes are feasible in existing hardware. Moreover, we present an evaluation that suggests that moving Paxos logic into the network would yield significant performance benefits for distributed applications.
{"title":"NetPaxos: consensus at network speed","authors":"Huynh Tu Dang, Daniele Sciascia, M. Canini, F. Pedone, R. Soulé","doi":"10.1145/2774993.2774999","DOIUrl":"https://doi.org/10.1145/2774993.2774999","url":null,"abstract":"This paper explores the possibility of implementing the widely deployed Paxos consensus protocol in network devices. We present two different approaches: (i) a detailed design description for implementing the full Paxos logic in SDN switches, which identifies a sufficient set of required OpenFlow extensions; and (ii) an alternative, optimistic protocol which can be implemented without changes to the OpenFlow API, but relies on assumptions about how the network orders messages. Although neither of these protocols can be fully implemented without changes to the underlying switch firmware, we argue that such changes are feasible in existing hardware. Moreover, we present an evaluation that suggests that moving Paxos logic into the network would yield significant performance benefits for distributed applications.","PeriodicalId":316190,"journal":{"name":"Proceedings of the 1st ACM SIGCOMM Symposium on Software Defined Networking Research","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-06-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117286680","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}
With the rise of video streaming and cloud services, enterprise and access networks receive much more traffic than they send, and must rely on the Internet to offer good end-to-end performance. These edge networks often connect to multiple ISPs for better performance and reliability, but have only limited ways to influence which of their ISPs carries the traffic for each service. In this paper, we present Sprite, a software-defined solution for flexible inbound traffic engineering (TE). Sprite offers direct, fine-grained control over inbound traffic, by announcing different public IP prefixes to each ISP, and performing source network address translation (SNAT) on outbound request traffic. Our design achieves scalability in both the data plane (by performing SNAT on edge switches close to the clients) and the control plane (by having local agents install the SNAT rules). The controller translates high-level TE objectives, based on client and server names, as well as performance metrics, to a dynamic network policy based on real-time traffic and performance measurements. We evaluate Sprite with live data from "in the wild" experiments on an EC2-based testbed, and demonstrate how Sprite dynamically adapts the network policy to achieve high-level TE objectives, such as balancing YouTube traffic among ISPs to improve video quality.
{"title":"Scalable programmable inbound traffic engineering","authors":"Peng Sun, L. Vanbever, J. Rexford","doi":"10.1145/2774993.2775063","DOIUrl":"https://doi.org/10.1145/2774993.2775063","url":null,"abstract":"With the rise of video streaming and cloud services, enterprise and access networks receive much more traffic than they send, and must rely on the Internet to offer good end-to-end performance. These edge networks often connect to multiple ISPs for better performance and reliability, but have only limited ways to influence which of their ISPs carries the traffic for each service. In this paper, we present Sprite, a software-defined solution for flexible inbound traffic engineering (TE). Sprite offers direct, fine-grained control over inbound traffic, by announcing different public IP prefixes to each ISP, and performing source network address translation (SNAT) on outbound request traffic. Our design achieves scalability in both the data plane (by performing SNAT on edge switches close to the clients) and the control plane (by having local agents install the SNAT rules). The controller translates high-level TE objectives, based on client and server names, as well as performance metrics, to a dynamic network policy based on real-time traffic and performance measurements. We evaluate Sprite with live data from \"in the wild\" experiments on an EC2-based testbed, and demonstrate how Sprite dynamically adapts the network policy to achieve high-level TE objectives, such as balancing YouTube traffic among ISPs to improve video quality.","PeriodicalId":316190,"journal":{"name":"Proceedings of the 1st ACM SIGCOMM Symposium on Software Defined Networking Research","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-06-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116177451","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}
Software-Defined Networking (SDN) switch vendors are interested in extending switch data planes to support new and continuously evolving network protocols (e.g., NVGRE, VXLAN). Numerous commercial programmable data plane devices already enable a programmer to specify various aspects of the data plane including packet parsing, actions, and the layout of packet processing on the hardware device itself. Unlike OpenFlow-based devices, which only expose a series of fixed match-action table (MAT) abstraction, these specialized devices provide a more flexible abstraction for packet processing. Despite the increased programmability that these devices offer, however, the architecture of the target restricts the features that can be exposed to the programmer. Similarly, existing languages for programming the data planes in such devices (e.g., P4) assume a specific computational model, resembling the architecture of the device for which they are targeted for. Unfortunately, this model leads to similar limitations as in OpenFlow, where the high-level specification is coupled to the underlying device model. In this paper, we introduce NetASM, an intermediate representation for programmable data planes. NetASM is a device-independent language that is expressive enough to act as the target language for compilers for high-level languages, yet low-level enough to be efficiently assembled on various device architectures. It enables conventional compiler optimization techniques to significantly improve the performance and resource utilization of custom packet-processing pipelines on a variety of targets.
{"title":"The case for an intermediate representation for programmable data planes","authors":"M. Shahbaz, N. Feamster","doi":"10.1145/2774993.2775000","DOIUrl":"https://doi.org/10.1145/2774993.2775000","url":null,"abstract":"Software-Defined Networking (SDN) switch vendors are interested in extending switch data planes to support new and continuously evolving network protocols (e.g., NVGRE, VXLAN). Numerous commercial programmable data plane devices already enable a programmer to specify various aspects of the data plane including packet parsing, actions, and the layout of packet processing on the hardware device itself. Unlike OpenFlow-based devices, which only expose a series of fixed match-action table (MAT) abstraction, these specialized devices provide a more flexible abstraction for packet processing. Despite the increased programmability that these devices offer, however, the architecture of the target restricts the features that can be exposed to the programmer. Similarly, existing languages for programming the data planes in such devices (e.g., P4) assume a specific computational model, resembling the architecture of the device for which they are targeted for. Unfortunately, this model leads to similar limitations as in OpenFlow, where the high-level specification is coupled to the underlying device model. In this paper, we introduce NetASM, an intermediate representation for programmable data planes. NetASM is a device-independent language that is expressive enough to act as the target language for compilers for high-level languages, yet low-level enough to be efficiently assembled on various device architectures. It enables conventional compiler optimization techniques to significantly improve the performance and resource utilization of custom packet-processing pipelines on a variety of targets.","PeriodicalId":316190,"journal":{"name":"Proceedings of the 1st ACM SIGCOMM Symposium on Software Defined Networking Research","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-06-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116248950","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}
SDN-enabled datacenter network management and debugging can benefit by the ability to trace packet trajectories. For example, such a functionality allows measuring traffic matrix, detecting traffic anomalies, localizing network faults, etc. Existing techniques for tracing packet trajectories require either large data collection overhead or large amount of data plane resources such as switch flow rules and packet header space. We present CherryPick, a scalable, yet simple technique for tracing packet trajectories. The core idea of our technique is to cherry-pick the links that are key to representing an end-to-end path of a packet, and to embed them into its header on its way to destination. Preliminary evaluation on a fat-tree topology shows that CherryPick requires minimal switch flow rules, while using header space close to state-of-the-art techniques.
{"title":"CherryPick: tracing packet trajectory in software-defined datacenter networks","authors":"Praveen Tammana, R. Agarwal, Myungjin Lee","doi":"10.1145/2774993.2775066","DOIUrl":"https://doi.org/10.1145/2774993.2775066","url":null,"abstract":"SDN-enabled datacenter network management and debugging can benefit by the ability to trace packet trajectories. For example, such a functionality allows measuring traffic matrix, detecting traffic anomalies, localizing network faults, etc. Existing techniques for tracing packet trajectories require either large data collection overhead or large amount of data plane resources such as switch flow rules and packet header space. We present CherryPick, a scalable, yet simple technique for tracing packet trajectories. The core idea of our technique is to cherry-pick the links that are key to representing an end-to-end path of a packet, and to embed them into its header on its way to destination. Preliminary evaluation on a fat-tree topology shows that CherryPick requires minimal switch flow rules, while using header space close to state-of-the-art techniques.","PeriodicalId":316190,"journal":{"name":"Proceedings of the 1st ACM SIGCOMM Symposium on Software Defined Networking Research","volume":"106 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-06-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115813576","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}
Sergey Guenender, K. Barabash, Y. Ben-Itzhak, A. Levin, E. Raichstein, L. Schour
Overlay network virtualization quickly gains traction in today's multi-tenant data centers due to its ability to provide independent virtual networks, at scale, along with complete isolation from the underlying physical network. Despite the benefits, performance degradation due to the imposed perpacket encapsulation overhead is a serious impediment. Mitigation approaches are mostly hardware based and thus depend on costly networking gear upgrades and suffer from lesser flexibility and longer times to market, compared to software solutions. Software optimizations proposed so far are limited in scope, applicability, and interoperability. In this paper we present NoEncap, a software-only opt mization, capable of eliminating almost completely the overheads, while fully preserving the benefits of an overlay-based network virtualization.
{"title":"NoEncap: overlay network virtualization with no encapsulation overheads","authors":"Sergey Guenender, K. Barabash, Y. Ben-Itzhak, A. Levin, E. Raichstein, L. Schour","doi":"10.1145/2774993.2775003","DOIUrl":"https://doi.org/10.1145/2774993.2775003","url":null,"abstract":"Overlay network virtualization quickly gains traction in today's multi-tenant data centers due to its ability to provide independent virtual networks, at scale, along with complete isolation from the underlying physical network. Despite the benefits, performance degradation due to the imposed perpacket encapsulation overhead is a serious impediment. Mitigation approaches are mostly hardware based and thus depend on costly networking gear upgrades and suffer from lesser flexibility and longer times to market, compared to software solutions. Software optimizations proposed so far are limited in scope, applicability, and interoperability. In this paper we present NoEncap, a software-only opt mization, capable of eliminating almost completely the overheads, while fully preserving the benefits of an overlay-based network virtualization.","PeriodicalId":316190,"journal":{"name":"Proceedings of the 1st ACM SIGCOMM Symposium on Software Defined Networking Research","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-06-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127718640","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：