Modern data center networks are usually constructed in multi-rooted tree topologies, which require the highly efficient multi-path load balancing to achieve high link utilization. Recent packet-level load balancer obtains high throughput by spraying packets to all paths, but it easily leads to the packet reordering under network asymmetry. The flow-level or flowlet-level load balancer avoids the packet reordering, while reducing the link utilization due to their inflexibility. To solve these problems, we design a Queueing Delay Aware Packet Spraying (QDAPS), that effectively mitigates the packet reordering for packet-level load balancer. QDAPS selects paths for packets according to the queueing delay of output buffer, and lets the packet arriving earlier be forwarded before the later packets to avoid packet reordering. We compare QDAPS with ECMP, LetFlow and RPS through NS2 simulation and Mininet implementation. The test results show that QDAPS reduces flow completion time (FCT) by ∼30%-50% over the state-of-the-art load balancing mechanism.
|Original language||English (US)|
|Title of host publication||Proceedings - 26th IEEE International Conference on Network Protocols, ICNP 2018|
|Publisher||IEEE Computer Society|
|Number of pages||11|
|State||Published - Nov 7 2018|
|Event||26th IEEE International Conference on Network Protocols, ICNP 2018 - Cambridge, United Kingdom|
Duration: Sep 24 2018 → Sep 27 2018
|Name||Proceedings - International Conference on Network Protocols, ICNP|
|Other||26th IEEE International Conference on Network Protocols, ICNP 2018|
|Period||9/24/18 → 9/27/18|
Bibliographical noteFunding Information:
This work is supported by the National Natural Science Foundation of China (61572530, 61629302 and 61420106009), CERNET Innovation Project (Grant No.NGII20160113) and Fundamental Research Funds for Central Universities of Central South University (2018zzts066).
- Data center
- Load balancing