With an ever increasing demand for computing power, number of nodes to be deployed in a cluster based supercomputer is increasing. Limited hardware resources such as Endpoints on HCA of a high speed interconnect limit the scalability of a parallel application based on MPI that sets up reliable connections between every process pair using endpoints, prior to communication. In this paper, we propose a novel approach of multiplexing endpoints to extend scalability. We discuss critical design issues in connection management and data transfer routines with the multiplexing technique. Using this approach, we are able to scale up MPI applications with nearly equal or better performance with the same HCA.
{"title":"Multiplexing endpoints of HCA to achieve scalability for MPI applications: design, implementation and performance evaluation with uDAPL","authors":"Jasjit Singh, Yogeshwar Sonawane","doi":"10.1145/1882486.1882505","DOIUrl":"https://doi.org/10.1145/1882486.1882505","url":null,"abstract":"With an ever increasing demand for computing power, number of nodes to be deployed in a cluster based supercomputer is increasing. Limited hardware resources such as Endpoints on HCA of a high speed interconnect limit the scalability of a parallel application based on MPI that sets up reliable connections between every process pair using endpoints, prior to communication. In this paper, we propose a novel approach of multiplexing endpoints to extend scalability. We discuss critical design issues in connection management and data transfer routines with the multiplexing technique. Using this approach, we are able to scale up MPI applications with nearly equal or better performance with the same HCA.","PeriodicalId":329300,"journal":{"name":"Symposium on Architectures for Networking and Communications Systems","volume":"73 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115171436","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}
Mario A. Gomez-Rodriguez, Víctor Jesús Sosa Sosa, I. Lopez-Arevalo
This paper introduces an external storage middleware, that offers a set of functions (API - Application Program Interface) to mobile applications and facilitates the transfer of files between a mobile device and external storage servers regardless of the available wireless network. The Middleware selects the best wireless service available. In addition, the files exchanged between the mobile device and the external storage server are encrypted to provide security when traveling through the network. As a use case, it was developed an automatic file swapper service for mobile devices. The service is running on the mobile device optimizing its available storage space. Our middleware was tested with the following wireless services: Wi-Fi, GPRS, MMS.
{"title":"External storage middleware for wireless devices with limited resources","authors":"Mario A. Gomez-Rodriguez, Víctor Jesús Sosa Sosa, I. Lopez-Arevalo","doi":"10.1145/1882486.1882530","DOIUrl":"https://doi.org/10.1145/1882486.1882530","url":null,"abstract":"This paper introduces an external storage middleware, that offers a set of functions (API - Application Program Interface) to mobile applications and facilitates the transfer of files between a mobile device and external storage servers regardless of the available wireless network. The Middleware selects the best wireless service available. In addition, the files exchanged between the mobile device and the external storage server are encrypted to provide security when traveling through the network. As a use case, it was developed an automatic file swapper service for mobile devices. The service is running on the mobile device optimizing its available storage space. Our middleware was tested with the following wireless services: Wi-Fi, GPRS, MMS.","PeriodicalId":329300,"journal":{"name":"Symposium on Architectures for Networking and Communications Systems","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114491410","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}
We describe the implementation of a URL-based forwarding function on a network processor-based programmable router (NPR). URL-based forwarding is an important tool for overlay networks. This paper presents a data path for overlay networks and the effectiveness of a programmable router.
{"title":"Implementing URL-based forwarding on a network processor-based router platform","authors":"Toshiro Yamauchi, Haowei Yuan, P. Crowley","doi":"10.1145/1882486.1882527","DOIUrl":"https://doi.org/10.1145/1882486.1882527","url":null,"abstract":"We describe the implementation of a URL-based forwarding function on a network processor-based programmable router (NPR). URL-based forwarding is an important tool for overlay networks. This paper presents a data path for overlay networks and the effectiveness of a programmable router.","PeriodicalId":329300,"journal":{"name":"Symposium on Architectures for Networking and Communications Systems","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128532054","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 radio is a deceptively simple idea: Identify all the features that specialize an RF communications device to a particular waveform (e.g. GSM cell phone or FM walkie talkie), and implement these features in flexible software on a generic platform, rather than in fixed-function hardware. This change should provide significant advantages compared to legacy hardware radios: the ability to support multiple waveforms on the same device, to upgrade the waveforms on the device through software downloads, and to dynamically adapt modulation or other physical layer parameters to a wide range of channel conditions. However, taking full advantage of software radio turns out to require a broad change in communications systems. Affected hardware components include antennas, filters, A/D converters, and power amplifiers. Affected device-level software components include signal processing, timing control, inter-layer APIs, and security. The hardware architectures optimal for this software are not GPPs, DSPs or FPGAs, but an interesting hybrid among these approaches. At the network level, new MAC algorithms and topology management are needed to exploit the flexibility of individual nodes. In this talk I present a slice through these varied and interrelated systems and research challenges, taking a total systems view of software radio.
{"title":"Software radio: a broad change in RF communications systems design","authors":"J. Chapin","doi":"10.1145/1882486.1882487","DOIUrl":"https://doi.org/10.1145/1882486.1882487","url":null,"abstract":"Software radio is a deceptively simple idea: Identify all the features that specialize an RF communications device to a particular waveform (e.g. GSM cell phone or FM walkie talkie), and implement these features in flexible software on a generic platform, rather than in fixed-function hardware. This change should provide significant advantages compared to legacy hardware radios: the ability to support multiple waveforms on the same device, to upgrade the waveforms on the device through software downloads, and to dynamically adapt modulation or other physical layer parameters to a wide range of channel conditions. However, taking full advantage of software radio turns out to require a broad change in communications systems. Affected hardware components include antennas, filters, A/D converters, and power amplifiers. Affected device-level software components include signal processing, timing control, inter-layer APIs, and security. The hardware architectures optimal for this software are not GPPs, DSPs or FPGAs, but an interesting hybrid among these approaches. At the network level, new MAC algorithms and topology management are needed to exploit the flexibility of individual nodes. In this talk I present a slice through these varied and interrelated systems and research challenges, taking a total systems view of software radio.","PeriodicalId":329300,"journal":{"name":"Symposium on Architectures for Networking and Communications Systems","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114801458","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}
S. Nikolidakis, V. Giotsas, D. Vergados, C. Douligeris
The advent of Wireless Body-Area Sensor Networks (WBASNs) technologies enables the autonomic and remote collection of realtime physiological data related to the health status of patients with chronic diseases. At the same time the advances in wireless communication systems make possible the "anywhere, anytime" delivery of such data to medical staff and caregivers in order to allow them to easily monitor and quickly respond in emergencies. In this paper, we propose a system architecture that utilizes the IMS (IP Multimedia Subsystem) and the HL7 (Health Level Seven) technologies to implement a mobile and interoperable healthcare system to support WBASNs in a healthcare environment.
{"title":"A mobile healthcare system using IMS and the HL7 framework","authors":"S. Nikolidakis, V. Giotsas, D. Vergados, C. Douligeris","doi":"10.1145/1882486.1882535","DOIUrl":"https://doi.org/10.1145/1882486.1882535","url":null,"abstract":"The advent of Wireless Body-Area Sensor Networks (WBASNs) technologies enables the autonomic and remote collection of realtime physiological data related to the health status of patients with chronic diseases. At the same time the advances in wireless communication systems make possible the \"anywhere, anytime\" delivery of such data to medical staff and caregivers in order to allow them to easily monitor and quickly respond in emergencies. In this paper, we propose a system architecture that utilizes the IMS (IP Multimedia Subsystem) and the HL7 (Health Level Seven) technologies to implement a mobile and interoperable healthcare system to support WBASNs in a healthcare environment.","PeriodicalId":329300,"journal":{"name":"Symposium on Architectures for Networking and Communications Systems","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131044830","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}
Customizable packet processing is an important aspect of next-generation networks. Packet processing architectures using multi-core systems on a chip can be difficult to program. In our work, we propose a new packet processor design that simplifies packet processing by managing packet contexts in hardware. We show how such a design scales to large systems. Our results also show that the management of such a system is feasible with the proposed mapping algorithm.
{"title":"Simplifying data path processing in next-generation routers","authors":"Qiang Wu, D. Chasaki, T. Wolf","doi":"10.1145/1882486.1882492","DOIUrl":"https://doi.org/10.1145/1882486.1882492","url":null,"abstract":"Customizable packet processing is an important aspect of next-generation networks. Packet processing architectures using multi-core systems on a chip can be difficult to program. In our work, we propose a new packet processor design that simplifies packet processing by managing packet contexts in hardware. We show how such a design scales to large systems. Our results also show that the management of such a system is feasible with the proposed mapping algorithm.","PeriodicalId":329300,"journal":{"name":"Symposium on Architectures for Networking and Communications Systems","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115940521","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}
Yan Luo, Pablo Cascón, E. Murray, Julio Ortega Lopera
OpenFlow switching enables flexible management of enterprise network switches and experiments on regular network traffic. We present in this paper a complementary design to OpenFlow's existing reference designs. We apply network processor based acceleration cards to perform OpenFlow switching. We describe the design options and report our experiment results that show a 20% reduction on packet delay and the comparable packet forwarding throughput compared to conventional designs.
{"title":"Accelerating OpenFlow switching with network processors","authors":"Yan Luo, Pablo Cascón, E. Murray, Julio Ortega Lopera","doi":"10.1145/1882486.1882504","DOIUrl":"https://doi.org/10.1145/1882486.1882504","url":null,"abstract":"OpenFlow switching enables flexible management of enterprise network switches and experiments on regular network traffic. We present in this paper a complementary design to OpenFlow's existing reference designs. We apply network processor based acceleration cards to perform OpenFlow switching. We describe the design options and report our experiment results that show a 20% reduction on packet delay and the comparable packet forwarding throughput compared to conventional designs.","PeriodicalId":329300,"journal":{"name":"Symposium on Architectures for Networking and Communications Systems","volume":"122 ","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132948363","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}
Local interconnect architectures are at a cusp in which advances in throughput have come at the expense of power and latency. Moreover, physical limits imposed on dissipation and packaging mean that further advances will require a new approach to interconnect design. Although latency in networks has been the focus of the High-Performance Computing architect and of concern across the computer community, we illustrate how an evolution in the common PCI interconnect architecture has worsened latency by a factor of between 3 and 25 over earlier incarnations.
{"title":"Motivating future interconnects: a differential measurement analysis of PCI latency","authors":"David J. Miller, P. Watts, A. Moore","doi":"10.1145/1882486.1882513","DOIUrl":"https://doi.org/10.1145/1882486.1882513","url":null,"abstract":"Local interconnect architectures are at a cusp in which advances in throughput have come at the expense of power and latency. Moreover, physical limits imposed on dissipation and packaging mean that further advances will require a new approach to interconnect design. Although latency in networks has been the focus of the High-Performance Computing architect and of concern across the computer community, we illustrate how an evolution in the common PCI interconnect architecture has worsened latency by a factor of between 3 and 25 over earlier incarnations.","PeriodicalId":329300,"journal":{"name":"Symposium on Architectures for Networking and Communications Systems","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115649232","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}
Ubiquitous multi-core-based web servers and edge routers are increasingly popular in deploying computationally intensive Deep Packet Inspection (DPI) programs. Previous work has shown the benefits of connection locality-based scheduling on multi-core servers to improve L7-filter performance. However, we show that highly threaded hierarchical multi-core processors, such as the Sun Niagara 2 processor, accumulate imbalanced workload at each resource layer. This workload imbalance potentially offsets the benefits from connection locality. In addition, connection-locality-based load balance fails to work when network traffic is unevenly distributed. In this paper, we propose an adaptive hash-based multilayer scheduler for a highly threaded hierarchical Sun Niagara 2 server. Our scheduler maintains connection locality and adaptively adjusts the scheduling to balance the real time workload. The original Highest Random Weight (HRW) hash guarantees the connection locality but only balances the workload over the number of different connections. We enhance the original single layer HRW into a hierarchical "hash tree" scheduler to balance the connection workload in accordance with the hierarchical processor architecture. We then optimize our multilayer scheduler to adaptively adjust scheduling decisions based on service time at each level, further improving the system load balance. Our scheduler is shown to increase the system throughput by 59.2% compared to the previously proposed connection locality optimization.
{"title":"An adaptive hash-based multilayer scheduler for L7-filter on a highly threaded hierarchical multi-core server","authors":"Danhua Guo, Guangdeng Liao, L. Bhuyan, B. Liu","doi":"10.1145/1882486.1882497","DOIUrl":"https://doi.org/10.1145/1882486.1882497","url":null,"abstract":"Ubiquitous multi-core-based web servers and edge routers are increasingly popular in deploying computationally intensive Deep Packet Inspection (DPI) programs. Previous work has shown the benefits of connection locality-based scheduling on multi-core servers to improve L7-filter performance. However, we show that highly threaded hierarchical multi-core processors, such as the Sun Niagara 2 processor, accumulate imbalanced workload at each resource layer. This workload imbalance potentially offsets the benefits from connection locality. In addition, connection-locality-based load balance fails to work when network traffic is unevenly distributed.\u0000 In this paper, we propose an adaptive hash-based multilayer scheduler for a highly threaded hierarchical Sun Niagara 2 server. Our scheduler maintains connection locality and adaptively adjusts the scheduling to balance the real time workload. The original Highest Random Weight (HRW) hash guarantees the connection locality but only balances the workload over the number of different connections. We enhance the original single layer HRW into a hierarchical \"hash tree\" scheduler to balance the connection workload in accordance with the hierarchical processor architecture. We then optimize our multilayer scheduler to adaptively adjust scheduling decisions based on service time at each level, further improving the system load balance. Our scheduler is shown to increase the system throughput by 59.2% compared to the previously proposed connection locality optimization.","PeriodicalId":329300,"journal":{"name":"Symposium on Architectures for Networking and Communications Systems","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126673773","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 increasingly open environment of mobile computing systems such as PDAs and smartphones brings rich applications and services to mobile users. Accompanied with this trend is the growing malicious activities against these mobile systems, such as information leakage, service stealing, and power exhaustion. Besides the threats posed against individual mobile users, these unveiled mobile devices also open the door for more serious damage such as disabling critical public cyber physical systems that are connected to the mobile/wireless infrastructure. The impact of such attacks, however, has not been fully recognized. In this work, we show that mobile devices, even with the state-of-the-art security mechanisms, are still vulnerable to a set of carefully crafted attacks. Taking Linux-based cell-phones as an example, we show that this vulnerability not only makes it possible to attack individual mobile devices such as accessing unauthorized resources, disabling predefined security mechanisms, and diverting phone calls, but also can be exploited to launch distributed denial-of-service attacks against critical public services such as 911. Using the open multi-class queuing network model, we analyze in detail the consequence of these attacks against the 911 service in a large region and also present some unique characteristics of these attacks. We further discuss potential countermeasures that can effectively mitigate or eliminate these attacks.
{"title":"Exploitation and threat analysis of open mobile devices","authors":"Lei Liu, Xinwen Zhang, Guanhua Yan, Songqing Chen","doi":"10.1145/1882486.1882493","DOIUrl":"https://doi.org/10.1145/1882486.1882493","url":null,"abstract":"The increasingly open environment of mobile computing systems such as PDAs and smartphones brings rich applications and services to mobile users. Accompanied with this trend is the growing malicious activities against these mobile systems, such as information leakage, service stealing, and power exhaustion. Besides the threats posed against individual mobile users, these unveiled mobile devices also open the door for more serious damage such as disabling critical public cyber physical systems that are connected to the mobile/wireless infrastructure. The impact of such attacks, however, has not been fully recognized.\u0000 In this work, we show that mobile devices, even with the state-of-the-art security mechanisms, are still vulnerable to a set of carefully crafted attacks. Taking Linux-based cell-phones as an example, we show that this vulnerability not only makes it possible to attack individual mobile devices such as accessing unauthorized resources, disabling predefined security mechanisms, and diverting phone calls, but also can be exploited to launch distributed denial-of-service attacks against critical public services such as 911. Using the open multi-class queuing network model, we analyze in detail the consequence of these attacks against the 911 service in a large region and also present some unique characteristics of these attacks. We further discuss potential countermeasures that can effectively mitigate or eliminate these attacks.","PeriodicalId":329300,"journal":{"name":"Symposium on Architectures for Networking and Communications Systems","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126425106","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：