Per-flow Queuing Memory Management without Per-flow Queues in High Speed Routers
نویسندگان
چکیده
Packet buffering in high speed routers requires a memory management unit to maintain the structure of the queues. With the dramatic increase in link speed and number of traffic flows, per-flow queuing becomes more and more challenging for the memory management unit since millions of queues should be maintained. To address this issue, a scheme called Dynamic Queue Sharing (DQS) is proposed in this paper. DQS is based on the following observation: at any specific moment in a high speed router, the packet buffers are occupied only by a few flows. In DQS only a few physical queues are implemented in hardware and they are shared by all the flows. Theoretical analysis and extensive simulations of the DQS scheme show that the number of physical queues implemented in hardware can be greatly reduced to hundreds in high speed routers. Cost and power consumption of the memory management unit can be significantly reduced accordingly. Keywords-Packet Buffers; Memory Management; Per-flow Queuing
منابع مشابه
Dynamic queuing sharing mechanism for per-flow quality of service control
To achieve satisfying user experiences of diverse applications, quality of service (QoS) guaranteed mechanisms such as per-flow queuing are required in routers. However, deployment of per-flow queuing in high-speed routers is considered as a great challenge since its industrial brute-force implementation is not scalable with the increase of the number of flows. In this study, the authors propos...
متن کاملHierarchically Aggregated Fair Queueing (HAFQ) for Per-Flow Fair Bandwidth Allocation
Because of the development of recent broadband access technologies, fair service among users is becoming more important goal. The most promising router mechanisms for providing fair service is per–flow traffic management. However, it is difficult to implement in high–speed core routers because per– flow state management is prohibitively expensive; thus, a large number of flows are aggregated in...
متن کاملAchieving per-flow Queueing Performance without a per-flow Queue
Recent studies have shown that suitably-designed packet discard policies can dramatically improve the performance of fair queueing mechanisms in internet routers. The Queue State Deficit Round Robin algorithm (QSDRR) preferentially discards from long queues, but introduces hysteresis into the discard policy to minimize synchronization among TCP flows. QSDRR provides higher throughput and much b...
متن کاملHierarchically aggregated fair queueing (HAFQ) for per-flow fair bandwidth allocation in high speed networks
for Per-flow Fair Bandwidth Allocation in High Speed Networks Ichinoshin Maki†, Hideyuki Shimonishi‡, Tutomu Murase‡, Masayuki Murata†, Hideo Miyahara† †Graduate School of Information Science and Technology, Osaka University ‡Networking Research Labs, NEC Corporation E-mail: [email protected] Abstract— Because of the development of recent broadband access technologies, fair service among...
متن کاملCore-Stateless Labeling Fairness: An Integrated Architecture to Approximate Fair Bandwidth Allocations in High Speed Networks
Core-stateless mechanisms achieve better scalability by reducing the complexity of fair queuing, which usually needs to maintain states, manage buffers, and perform flow scheduling on a per-flow basis. However, they require per-packet relabeling in the core routers. In this paper, we propose a core-stateless fair bandwidth allocation scheme without maintaining per flow state in core routers. Fu...
متن کامل