CAPS: Fine-Tuning CCA Timing

2026-07-24

AI Summary

Existing datacenter transport protocols couple rate control with packet scheduling, causing steady-state queues to accumulate as flow count increases and degrading latency performance. This work proposes Clocked ACK-Paced Synchronization (CAPS), which decouples rate control from scheduling and precisely regulates the timing of packet arrivals at the bottleneck link under a given stable rate, thereby reframing queuing as a timing alignment problem. CAPS introduces an ACK-clock-based phase-locking mechanism that employs a lightweight distributed scheduling layer to compensate for heterogeneous round-trip times (RTTs) and partitions bottleneck time into slots aligned with the ACK clock to enable inter-flow phase correction. Experimental results demonstrate that CAPS reduces worst-case queue occupancy by 5–10× across diverse topologies and traffic patterns while sustaining full throughput.

Abstract

Data-center congestion control targets high throughput, fair bandwidth allocation, and low latency. Modern transports couple rate computation and packet scheduling into a single feedback loop, converging to near-optimal rates but leaving standing queues that can scale with the number of flows. We argue that separating the two reveals a simpler design point. Given stable feasible rates, the residual queue problem reduces to a timing problem: if every flow's packets arrive at the bottleneck in the correct slot, the link stays busy and the queue stays empty. Clocked ACK-Paced Synchronization CAPS is a lightweight distributed scheduling layer that achieves this by phase-locking each sender's transmissions to ACK-clocked bottleneck slots, with a per-flow correction that compensates for heterogeneous RTTs. We characterize the phase-locked steady state for dumbbell topologies under equal RTT, heterogeneous RTT, and bidirectional traffic, and validate the mechanism on a fat-tree under incast, permutation, and all-to-all traffic. CAPS reduces worst-case queue occupancy by 5-10x across all tested scenarios without throughput loss.

Problem

• congestion control
• queue occupancy
• packet scheduling
• data-center networks
• standing queues

Innovation

• CAPS
• congestion control
• ACK-paced synchronization
• queue minimization
• distributed scheduling