CARL: Cost-Optimized Online Container Placement on VMs Using Adversarial Reinforcement Learning

Containerization has become popular for the deployment of applications on public clouds. Large enterprises may host 100 s of applications on 1000 s containers that are placed onto Virtual Machines (VMs). Such placement decisions happen continuously as applications are updated by DevOps pipelines that deploy the containers. Managing the placement of container resource requests onto the available capacities of VMs needs to be cost-efficient. This is well-studied, and usually modelled as a multi-dimensional Vector Bin-packing Problem (VBP). Many heuristics, and recently machine learning approaches, have been developed to solve this NP-hard problem for real-time decisions. We propose CARL, a novel approach to solve VBP through Adversarial Reinforcement Learning (RL) for cost minimization. It mimics the placement behavior of an offline semi-optimal VBP solver (teacher), while automatically learning a reward function for reducing the VM costs which out-performs the teacher. It requires limited historical container workload traces to train, and is resilient to changes in the workload distribution during inferencing. We extensively evaluate CARL on workloads derived from realistic traces from Google and Alibaba for the placement of 5 k–10 k container requests onto 2 k–8 k VMs, and compare it with classic heuristics and state-of-the-art RL methods. (1) CARL is <i>fast</i>, e.g., making placement decisions at <inline-formula><tex-math notation="LaTeX">$\approx 1900$</tex-math></inline-formula> requests/sec onto 8,900 candidate VMs. (2) It is <i>efficient</i>, achieving <inline-formula><tex-math notation="LaTeX">$\approx 16\%$</tex-math></inline-formula> lower VM costs than classic and contemporary RL methods. (3) It is <i>robust</i> to changes in the workload, offering competitive results even when the resource needs or inter-arrival time of the container requests skew from the training workload.