OpenFlow, originally proposed for campus and enterprise network experimentation, has become a promising SDN architecture that is considered as a widely-deployable production network node recently. It is, in a consequence, pointed out that OpenFlow cannot scale and replace today's versatile network devices due to its limited scalability and flexibility. In this paper, we propose OpenQFlow, a novel scalable and flexible variant of OpenFlow. OpenQFlow provides a fine-grained flow tracking while flow classification is decoupled from the tracking by separating the inefficiently coupled flow table to three different tables: flow state table, forwarding rule table, and QoS rule table. We also develop a two-tier flow-based QoS framework, derived from our new packet scheduling algorithm, which provides performance guarantee and fairness on both granularity levels of micro- and aggregate-flow at the same time. We have implemented OpenQFlow on an off-the-shelf microTCA chassis equipped with a commodity multicore processor, for which our architecture is suited, to achieve high-performance with carefully engineered software design and optimization.
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copy
Nam-Seok KO, Hwanjo HEO, Jong-Dae PARK, Hong-Shik PARK, "OpenQFlow: Scalable OpenFlow with Flow-Based QoS" in IEICE TRANSACTIONS on Communications,
vol. E96-B, no. 2, pp. 479-488, February 2013, doi: 10.1587/transcom.E96.B.479.
Abstract: OpenFlow, originally proposed for campus and enterprise network experimentation, has become a promising SDN architecture that is considered as a widely-deployable production network node recently. It is, in a consequence, pointed out that OpenFlow cannot scale and replace today's versatile network devices due to its limited scalability and flexibility. In this paper, we propose OpenQFlow, a novel scalable and flexible variant of OpenFlow. OpenQFlow provides a fine-grained flow tracking while flow classification is decoupled from the tracking by separating the inefficiently coupled flow table to three different tables: flow state table, forwarding rule table, and QoS rule table. We also develop a two-tier flow-based QoS framework, derived from our new packet scheduling algorithm, which provides performance guarantee and fairness on both granularity levels of micro- and aggregate-flow at the same time. We have implemented OpenQFlow on an off-the-shelf microTCA chassis equipped with a commodity multicore processor, for which our architecture is suited, to achieve high-performance with carefully engineered software design and optimization.
URL: https://global.ieice.org/en_transactions/communications/10.1587/transcom.E96.B.479/_p
Copy
@ARTICLE{e96-b_2_479,
author={Nam-Seok KO, Hwanjo HEO, Jong-Dae PARK, Hong-Shik PARK, },
journal={IEICE TRANSACTIONS on Communications},
title={OpenQFlow: Scalable OpenFlow with Flow-Based QoS},
year={2013},
volume={E96-B},
number={2},
pages={479-488},
abstract={OpenFlow, originally proposed for campus and enterprise network experimentation, has become a promising SDN architecture that is considered as a widely-deployable production network node recently. It is, in a consequence, pointed out that OpenFlow cannot scale and replace today's versatile network devices due to its limited scalability and flexibility. In this paper, we propose OpenQFlow, a novel scalable and flexible variant of OpenFlow. OpenQFlow provides a fine-grained flow tracking while flow classification is decoupled from the tracking by separating the inefficiently coupled flow table to three different tables: flow state table, forwarding rule table, and QoS rule table. We also develop a two-tier flow-based QoS framework, derived from our new packet scheduling algorithm, which provides performance guarantee and fairness on both granularity levels of micro- and aggregate-flow at the same time. We have implemented OpenQFlow on an off-the-shelf microTCA chassis equipped with a commodity multicore processor, for which our architecture is suited, to achieve high-performance with carefully engineered software design and optimization.},
keywords={},
doi={10.1587/transcom.E96.B.479},
ISSN={1745-1345},
month={February},}
Copy
TY - JOUR
TI - OpenQFlow: Scalable OpenFlow with Flow-Based QoS
T2 - IEICE TRANSACTIONS on Communications
SP - 479
EP - 488
AU - Nam-Seok KO
AU - Hwanjo HEO
AU - Jong-Dae PARK
AU - Hong-Shik PARK
PY - 2013
DO - 10.1587/transcom.E96.B.479
JO - IEICE TRANSACTIONS on Communications
SN - 1745-1345
VL - E96-B
IS - 2
JA - IEICE TRANSACTIONS on Communications
Y1 - February 2013
AB - OpenFlow, originally proposed for campus and enterprise network experimentation, has become a promising SDN architecture that is considered as a widely-deployable production network node recently. It is, in a consequence, pointed out that OpenFlow cannot scale and replace today's versatile network devices due to its limited scalability and flexibility. In this paper, we propose OpenQFlow, a novel scalable and flexible variant of OpenFlow. OpenQFlow provides a fine-grained flow tracking while flow classification is decoupled from the tracking by separating the inefficiently coupled flow table to three different tables: flow state table, forwarding rule table, and QoS rule table. We also develop a two-tier flow-based QoS framework, derived from our new packet scheduling algorithm, which provides performance guarantee and fairness on both granularity levels of micro- and aggregate-flow at the same time. We have implemented OpenQFlow on an off-the-shelf microTCA chassis equipped with a commodity multicore processor, for which our architecture is suited, to achieve high-performance with carefully engineered software design and optimization.
ER -