A high-resolution study of data center traffic at its origin

ABSTRACT

High-resolution studies of data center traffic at the network core uncover short-term bursty traffic patterns, periods of high buffer utilization that last for tens of microseconds and lead to packet loss and longer flow completion time tails. While recent attention has been directed towards studying the bursty traffic at the network core, less heed has been given to the origins of bursty traffic, e.g., host machines. In this study, we try to perform high-resolution traffic measurements in the host networking stack to quantify the impact of system software components on traffic burstiness. We enforce per-packet timestamping on the datapath using various techniques like NIC timestamping, eBPF, and direct kernel source modification and measure the gaps between egress packets under various configurations. We provide preliminary findings on how process scheduling can affect traffic burstiness.

References

1. Theophilus Benson et al. 2010. Network Traffic Characteristics of Data Centers in the Wild. In IMC.
2. Qizhe Cai et al. 2021. Understanding host network stack overheads. In SIGCOMM.
3. Xiaoqi Chen et al. 2019. Fine-grained queue measurement in the data plane. In CoNEXT.
4. Antoine Kaufmann et al. 2019. TAS: TCP Acceleration as an OS Service. In EuroSys.
5. Gautam Kumar et al. 2020. Swift: Delay is Simple and Effective for Congestion Control in the Datacenter. In SIGCOMM.
6. Michael Marty et al. 2019. Snap: A Microkernel Approach to Host Networking. In SOSP.
7. Arjun Roy et al. 2015. Inside the Social Network's (Datacenter) Network. In SIGCOMM.
8. D Shan et al. 2018. Micro-Burst in Data Centers: Observations, Analysis, and Mitigations. In ICNP.
9. Jackson Woodruff et al. 2019. Measuring Burstiness in Data Center Applications. In BS.
10. Qiao Zhang et al. 2017. High-resolution measurement of data center microbursts. In IMC.

Index Terms

• Networks

  • Network types

    • Data center networks