Flowbender: Flow-level adaptive routing for improved latency and throughput in datacenter networks

Datacenter networks provide high path diversity for traffic between machines. Load balancing traffic across these paths is important for both, latency- and throughput-sensitive ap-plications. The standard load balancing techniques used to-day obliviously hash a flow to a random path. When long flows collide on the same path, this might lead to long lasting congestion while other paths could be underutilized, degrad-ing performance of other flows as well. Recent proposals to address this shortcoming incur significant implementation complexity at the host that would actually slow down short flows (MPTCP), depend on relatively slow centralized con-trollers for rerouting large congesting flows (Hedera), or re-quire custom switch hardware, hindering near-term deploy-ment (DeTail). We propose FlowBender, a novel technique that: (1) Load balances distributively at the granularity of flows instead of packets, avoiding excessive packet reordering. (2) Uses end-host-driven rehashing to trigger dynamic flow-to-path assignment. (3) Recovers from link failures within a Re-transmit Timeout (RTO). (4) Amounts to less than 50 lines of critical kernel code and is readily deployable in commod-ity data centers today. (5) Is very robust and simple to tune. We evaluate FlowBender using both simulations and a real testbed implementation, and show that it improves average and tail latencies significantly compared to state of the art techniques without incurring the significant overhead and complexity of other load balancing schemes