Internet traffic doubles every three months, with web traffic accounting for more than 75% of the... more Internet traffic doubles every three months, with web traffic accounting for more than 75% of the total traffic between major ISP providers. Web caching at proxies can reduce this traffic as well as web user latencies. One way to increase the hit rate of caches is to have caches cooperate using the Internet Cache Protocol or using hash functions. This paper provides an experimental and theoretical analysis of two well known hash based caching schemes. Our paper also proposes a new allocation scheme which improves the performance of one of the analyzed techniques. It reduces the standard deviation of the URLs distribution on caches by a factor greater than two.
Peer-to-peer systems have recently introduced the notion of super-peers to improve search perform... more Peer-to-peer systems have recently introduced the notion of super-peers to improve search performance. While the benefit to end users is clear, it is not immediately evident who, if anyone, would be motivated to act as a super-peer. On the face of it, super-peers bear a much larger traffic burden than normal peers and receive negligible improvement in search performance when compared to any of the nodes they serve.
A communication network includes an access network element that delivers data to/from the user an... more A communication network includes an access network element that delivers data to/from the user and an associated core network element providing connectivity with the application servers. Multiconnectivity scenarios are common where a device can be simultaneously connected to multiple communication networks based on different technology implementations and network architectures like WiFi, LTE, DSL. A smart combination and selection of access and core network paths that can dynamically adapt to changing network conditions can improve quality of experience for a user in a multiconnectivity scenario and improve overall network utilization and efficiency. This document presents the problem statement and proposes solution principles. It specifies the requirements and reference architecture for a multi access management services framework that can be used to flexibly select the best combination of uplink and downlink access and core network paths, ensuring better network efficiency and enh...
Multithreading processors pose new challenges and new opportunities f or cache/memory hierarchy d... more Multithreading processors pose new challenges and new opportunities f or cache/memory hierarchy design. Multithreading significantly alters the data reference stream seen by the memory subsystem. Multithreading also demands very different performance characteristics from the cache hierarchy than a typical (uniprocessor) CPU. This paper is specifically concerned with memory hierarchy design considerations for simultaneous multithreading (SMT) processors [7]. While multithreading processors may have created a new memory throughput crisis, their latency-tolerance al so provides an opportunity. We can trade memory latency in various ways to buy increased throughput-to lerance. In this paper, we examine several ways to trade latency for throughput, as well as other m echanisms for increasing throughput-tolerance. We examine memory associativity, hierarchical cacheing, and cache block size in li ght of these new priorities. We also consider new cache replacement as a way to reduce the L1-...
In multiconnectivity scenarios, the end-user devices can simultaneously connect to multiple netwo... more In multiconnectivity scenarios, the end-user devices can simultaneously connect to multiple networks based on different access technologies and network architectures like WiFi, LTE, DSL. Both the quality of experience of the users and the overall network utilization and efficiency may be improved through the smart selection and combination of access and core network paths that can dynamically adapt to changing network conditions. This document presents a unified problem statement and introduces a solution for managing multiconnectivity. The solution has been developed by the authors based on their experiences in multiple standards bodies including the IETF and 3GPP, but is not an Internet Standard and does not represent the consensus opinion of the IETF. This document describes the requirements, solution principles, and an architectural framework that aims to provide best performance while being easy to implement in a wide variety of multiconnectivity deployments. It specifies the p...
Today, a device can be simultaneously connected to multiple communication networks based on diffe... more Today, a device can be simultaneously connected to multiple communication networks based on different technology implementations and network architectures like WiFi, LTE, DSL. In such multi- connectivity scenario, it is desirable to combine multiple access networks or select the best one to improve quality of experience for a user and improve overall network utilization and efficiency. This document presents the control plane protocols, as well as describes control plane procedures for configuring the user plane in a multi access management services (MAMS) framework that can be used to flexibly select the combination of uplink and downlink access and core network paths, and user plane treatment for improving network efficiency and enhanced application quality of experience.
Peer-to-peer systems have recently introduced the notion of super-peers to improve search perform... more Peer-to-peer systems have recently introduced the notion of super-peers to improve search performance. While the benefit to end users is clear, it is not immediately evident who, if anyone, would be motivated to act as a super-peer. On the face of it, super-peers bear a much larger traffic burden than normal peers and receive negligible improvement in search performance when compared to any of the nodes they serve. In this paper we present incentives for several actors to deploy super-peers and propose a novel technical mechanism, topic-based search optimization, to increase the effectiveness of super-peers. By caching meta data— as opposed to content—at super-peers, topic-based search optimization has the potential to significantly improve the perceived search performance of a super-peer’s clients with very modest storage and communication overhead at the super-peer itself.
In multiconnectivity scenarios, the end-user devices can simultaneously connect to multiple netwo... more In multiconnectivity scenarios, the end-user devices can simultaneously connect to multiple networks based on different access technologies and network architectures like WiFi, LTE, DSL. Both the quality of experience of the users and the overall network utilization and efficiency may be improved through the smart selection and combination of access and core network paths that can dynamically adapt to changing network conditions. This document presents a unified problem statement and introduces a solution for managing multiconnectivity. The solution has been developed by the authors based on their experiences in multiple standards bodies including the IETF and 3GPP, but is not an Internet Standard and does not represent the consensus opinion of the IETF. This document describes the requirements, solution principles, and an architectural framework that aims to provide best performance while being easy to implement in a wide variety of multiconnectivity deployments. It specifies the protocol multi-access management to: 1) flexibly select the best combination of access and core network paths for uplink and downlink; as well as 2) determine the user plane treatment and traffic distribution over the selected links ensuring network efficiency and application performance.
Pipelined forwarding engines are used in core routers to meet speed demands. Tree-based searches ... more Pipelined forwarding engines are used in core routers to meet speed demands. Tree-based searches are pipelined across a number of stages to achieve high throughput, but this results in unevenly distributed memory. To address this imbalance, conventional approaches use either complex dynamic memory allocation schemes or over-provision each of the pipeline stages. This paper describes the microarchitecture of a novel network search processor which provides both high execution throughput and balanced memory distribution by dividing the tree into subtrees and allocating each subtree separately, allowing searches to begin at any pipeline stage. The architecture is validated by implementing and simulating state of the art solutions for IPv4 lookup, VPN forwarding and packet classification. The new pipeline scheme and memory allocator can provide searches with a memory allocation efficiency that is within 1% of non-pipelined schemes.
A classifier consists of a set of rules for classifying packets based on header fields. Because c... more A classifier consists of a set of rules for classifying packets based on header fields. Because core routers can have fairly large (e.g., 2000 rule) database and must use limited SRAM to meet OC-768 speeds, the best existing classification algorithms (RFC, HiCuts, ABV) are precluded because of the large amount of memory they need. Thus the general belief is that hardware solutions like CAMs are needed, despite the amount of board area and power they consume. In this paper, we provide an alternative to CAMs via an Extended Grid-of-Tries with Path Compression (EGT-PC) algorithm whose worst-case speed scales well with database size while using a minimal amount of memory. Our evaluation is based on real databases used by Tier 1 ISPs, and synthetic databases. EGT-PC is based on a observation that we found holds for all the Tier 1 databases we studied: regardless of database size, any packet matches only a small number of distinct source-destination prefix pairs. The code we wrote for EGT...
A classifier consists of a set of rules for classifying packets based on header fields. Because c... more A classifier consists of a set of rules for classifying packets based on header fields. Because core routers can have fairly large (e.g., 2000 rule) database and must use limited SRAM to meet OC-768 speeds, the best existing classification algorithms (RFC, HiCuts, ABV) are precluded because of the large amount of memory they need. Thus the general belief is that hardware solutions like CAMs are needed, despite the amount of board area and power they consume. In this paper we provide an algorithm based on a fast search structure capable of providing search results with a throughput closer to the speed of the line where speed of the line may be OC 192, i.e. a packet every 32 ns. It is based on a decision tree in which each node can be seen as a k-dimensional hypercube, in which each dimension of the hypercube is associated with a dimension in the rules of the classifier. In each node a decision is taken based on information from one or multiple fields. The fields chosen to be used in ...
Internet traffic doubles every three months, with web traffic accounting for more than 75% of the... more Internet traffic doubles every three months, with web traffic accounting for more than 75% of the total traffic between major ISP providers. Web caching at proxies can reduce this traffic as well as web user latencies. One way to increase the hit rate of caches is to have caches cooperate using the Internet Cache Protocol or using hash functions. This paper provides an experimental and theoretical analysis of two well known hash based caching schemes. Our paper also proposes a new allocation scheme which improves the performance of one of the analyzed techniques. It reduces the standard deviation of the URLs distribution on caches by a factor greater than two.
Peer-to-peer systems have recently introduced the notion of super-peers to improve search perform... more Peer-to-peer systems have recently introduced the notion of super-peers to improve search performance. While the benefit to end users is clear, it is not immediately evident who, if anyone, would be motivated to act as a super-peer. On the face of it, super-peers bear a much larger traffic burden than normal peers and receive negligible improvement in search performance when compared to any of the nodes they serve.
A communication network includes an access network element that delivers data to/from the user an... more A communication network includes an access network element that delivers data to/from the user and an associated core network element providing connectivity with the application servers. Multiconnectivity scenarios are common where a device can be simultaneously connected to multiple communication networks based on different technology implementations and network architectures like WiFi, LTE, DSL. A smart combination and selection of access and core network paths that can dynamically adapt to changing network conditions can improve quality of experience for a user in a multiconnectivity scenario and improve overall network utilization and efficiency. This document presents the problem statement and proposes solution principles. It specifies the requirements and reference architecture for a multi access management services framework that can be used to flexibly select the best combination of uplink and downlink access and core network paths, ensuring better network efficiency and enh...
Multithreading processors pose new challenges and new opportunities f or cache/memory hierarchy d... more Multithreading processors pose new challenges and new opportunities f or cache/memory hierarchy design. Multithreading significantly alters the data reference stream seen by the memory subsystem. Multithreading also demands very different performance characteristics from the cache hierarchy than a typical (uniprocessor) CPU. This paper is specifically concerned with memory hierarchy design considerations for simultaneous multithreading (SMT) processors [7]. While multithreading processors may have created a new memory throughput crisis, their latency-tolerance al so provides an opportunity. We can trade memory latency in various ways to buy increased throughput-to lerance. In this paper, we examine several ways to trade latency for throughput, as well as other m echanisms for increasing throughput-tolerance. We examine memory associativity, hierarchical cacheing, and cache block size in li ght of these new priorities. We also consider new cache replacement as a way to reduce the L1-...
In multiconnectivity scenarios, the end-user devices can simultaneously connect to multiple netwo... more In multiconnectivity scenarios, the end-user devices can simultaneously connect to multiple networks based on different access technologies and network architectures like WiFi, LTE, DSL. Both the quality of experience of the users and the overall network utilization and efficiency may be improved through the smart selection and combination of access and core network paths that can dynamically adapt to changing network conditions. This document presents a unified problem statement and introduces a solution for managing multiconnectivity. The solution has been developed by the authors based on their experiences in multiple standards bodies including the IETF and 3GPP, but is not an Internet Standard and does not represent the consensus opinion of the IETF. This document describes the requirements, solution principles, and an architectural framework that aims to provide best performance while being easy to implement in a wide variety of multiconnectivity deployments. It specifies the p...
Today, a device can be simultaneously connected to multiple communication networks based on diffe... more Today, a device can be simultaneously connected to multiple communication networks based on different technology implementations and network architectures like WiFi, LTE, DSL. In such multi- connectivity scenario, it is desirable to combine multiple access networks or select the best one to improve quality of experience for a user and improve overall network utilization and efficiency. This document presents the control plane protocols, as well as describes control plane procedures for configuring the user plane in a multi access management services (MAMS) framework that can be used to flexibly select the combination of uplink and downlink access and core network paths, and user plane treatment for improving network efficiency and enhanced application quality of experience.
Peer-to-peer systems have recently introduced the notion of super-peers to improve search perform... more Peer-to-peer systems have recently introduced the notion of super-peers to improve search performance. While the benefit to end users is clear, it is not immediately evident who, if anyone, would be motivated to act as a super-peer. On the face of it, super-peers bear a much larger traffic burden than normal peers and receive negligible improvement in search performance when compared to any of the nodes they serve. In this paper we present incentives for several actors to deploy super-peers and propose a novel technical mechanism, topic-based search optimization, to increase the effectiveness of super-peers. By caching meta data— as opposed to content—at super-peers, topic-based search optimization has the potential to significantly improve the perceived search performance of a super-peer’s clients with very modest storage and communication overhead at the super-peer itself.
In multiconnectivity scenarios, the end-user devices can simultaneously connect to multiple netwo... more In multiconnectivity scenarios, the end-user devices can simultaneously connect to multiple networks based on different access technologies and network architectures like WiFi, LTE, DSL. Both the quality of experience of the users and the overall network utilization and efficiency may be improved through the smart selection and combination of access and core network paths that can dynamically adapt to changing network conditions. This document presents a unified problem statement and introduces a solution for managing multiconnectivity. The solution has been developed by the authors based on their experiences in multiple standards bodies including the IETF and 3GPP, but is not an Internet Standard and does not represent the consensus opinion of the IETF. This document describes the requirements, solution principles, and an architectural framework that aims to provide best performance while being easy to implement in a wide variety of multiconnectivity deployments. It specifies the protocol multi-access management to: 1) flexibly select the best combination of access and core network paths for uplink and downlink; as well as 2) determine the user plane treatment and traffic distribution over the selected links ensuring network efficiency and application performance.
Pipelined forwarding engines are used in core routers to meet speed demands. Tree-based searches ... more Pipelined forwarding engines are used in core routers to meet speed demands. Tree-based searches are pipelined across a number of stages to achieve high throughput, but this results in unevenly distributed memory. To address this imbalance, conventional approaches use either complex dynamic memory allocation schemes or over-provision each of the pipeline stages. This paper describes the microarchitecture of a novel network search processor which provides both high execution throughput and balanced memory distribution by dividing the tree into subtrees and allocating each subtree separately, allowing searches to begin at any pipeline stage. The architecture is validated by implementing and simulating state of the art solutions for IPv4 lookup, VPN forwarding and packet classification. The new pipeline scheme and memory allocator can provide searches with a memory allocation efficiency that is within 1% of non-pipelined schemes.
A classifier consists of a set of rules for classifying packets based on header fields. Because c... more A classifier consists of a set of rules for classifying packets based on header fields. Because core routers can have fairly large (e.g., 2000 rule) database and must use limited SRAM to meet OC-768 speeds, the best existing classification algorithms (RFC, HiCuts, ABV) are precluded because of the large amount of memory they need. Thus the general belief is that hardware solutions like CAMs are needed, despite the amount of board area and power they consume. In this paper, we provide an alternative to CAMs via an Extended Grid-of-Tries with Path Compression (EGT-PC) algorithm whose worst-case speed scales well with database size while using a minimal amount of memory. Our evaluation is based on real databases used by Tier 1 ISPs, and synthetic databases. EGT-PC is based on a observation that we found holds for all the Tier 1 databases we studied: regardless of database size, any packet matches only a small number of distinct source-destination prefix pairs. The code we wrote for EGT...
A classifier consists of a set of rules for classifying packets based on header fields. Because c... more A classifier consists of a set of rules for classifying packets based on header fields. Because core routers can have fairly large (e.g., 2000 rule) database and must use limited SRAM to meet OC-768 speeds, the best existing classification algorithms (RFC, HiCuts, ABV) are precluded because of the large amount of memory they need. Thus the general belief is that hardware solutions like CAMs are needed, despite the amount of board area and power they consume. In this paper we provide an algorithm based on a fast search structure capable of providing search results with a throughput closer to the speed of the line where speed of the line may be OC 192, i.e. a packet every 32 ns. It is based on a decision tree in which each node can be seen as a k-dimensional hypercube, in which each dimension of the hypercube is associated with a dimension in the rules of the classifier. In each node a decision is taken based on information from one or multiple fields. The fields chosen to be used in ...
Uploads