Janus: Risk based Planning of Network Changes in Data Centers

Abstract:

Data center networks are evolving fast while continuously serving customer traffic. When applying network changes, operators risk impacting customer traffic because the network operates at reduced capacity and is more vulnerable to failures and traffic variations while changes are being applied. The impact on customer traffic ultimately translates to operator cost (e.g., refunds to customers). However, planning a network change while minimizing the risks is challenging because we need to adapt to a variety of traffic dynamics and cost functions and scale to large networks and large changes. Today, operators mostly use plans that maximize the residual capacity which often incurs a high cost under different traffic dynamics. Instead, we propose Janus, which searches the large planning space by leveraging the high degree of symmetry in data center networks. Our evaluation on large Clos networks and Facebook traffic traces shows that Janus generates plans in real-time, which only needs 33~71% of the cost compared to MRC while being adaptive to a variety of settings.