Network-wide heavy hitter detection is usually performed by sampling on several network measurement points (NMPs) and merging the measurement results in the centralized controller to get a network-wide view. However, a packet may pass several NMPs and be counted multiple times when measurement results are merged, which causes the double-counting problem and leads to incorrect detection. Existing studies either overlook this problem or require significant memory usage. This paper proposes SAROS, a self-adaptive routing oblivious sampling method for accurate network-wide heavy hitter detection. Specifically, SAROS exploits a sampling mechanism in the data plane, where the sampling threshold on each measurement point is predicted and adaptively set by the control plane. Such guidance from the control plane greatly reduces the memory usage in the data plane, while mitigating the double-counting problem. Experimental results show that, compared with existing solutions, SAROS improves the F1-Score of heavy hitter detection by 10 ∼ 40%.
Modern DNS has evolved beyond traditional name resolution, increasingly serving as a carrier for structured metadata and service-discovery information. This functional enrichment inevitably drives sustained growth in DNS response payloads. While essential for modern ecosystem features, this growth is also making DNS response size the center of amplification risk. Despite its importance, the behavior of response size in the wild remains poorly understood, and we still lack a global, systematic view to guide its configuration and control. To this end, we conduct a year-long measurement of response-size behavior across about one million open DNS resolvers. We characterize the UDP response-size limits enforced by these resolvers and find that they cluster around a small set of common values. We also demonstrate how configuration changes at major public resolvers propagate across the DNS ecosystem. We further show that regional differences in resolver response-size limits lead to uneven amplification risk and expose fundamental limitations of existing static and upstream-based defenses. This complex response behavior stems from the tension between mitigating amplification risk through small fixed response-size limits and supporting diverse applications that require large responses. To address this tension, we propose Adaptive Response Scaling (ARS), a lightweight dynamic response-control mechanism that reduces amplification by over 70% while preserving DNS functionality.