In December 2022, we introduced our partnership with Isovalent to carry subsequent era prolonged Berkeley Packet Filter (eBPF) dataplane for cloud-native purposes in Microsoft Azure and it was revealed that the subsequent era of Azure Container Community Interface (CNI) dataplane could be powered by eBPF and Cilium.
Right this moment, we’re thrilled to announce the final availability of Azure CNI powered by Cilium. Azure CNI powered by Cilium is a next-generation networking platform that mixes two highly effective applied sciences: Azure CNI for scalable and versatile Pod networking management, built-in with the Azure Digital Community stack, and Cilium, an open-source mission that makes use of eBPF-powered information aircraft for networking, safety, and observability in Kubernetes. Azure CNI powered by Cilium takes benefit of Cilium’s direct routing mode inside visitor digital machines and combines it with the Azure native routing contained in the Azure community, enabling improved community efficiency for workloads deployed in Azure Kubernetes Service (AKS) clusters, and with inbuilt assist for imposing networking safety.
On this weblog, we are going to delve additional into the efficiency and scalability outcomes achieved via this highly effective networking providing in Azure Kubernetes Service.
Efficiency and scale outcomes
Efficiency exams are performed in AKS clusters in overlay mode to investigate system conduct and consider efficiency below heavy load circumstances. These exams simulate eventualities the place the cluster is subjected to excessive ranges of useful resource utilization, corresponding to massive concurrent requests or excessive workloads. The target is to measure numerous efficiency metrics like response occasions, throughput, scalability, and useful resource utilization to know the cluster’s conduct and determine any efficiency bottlenecks.
Service routing latency
The experiment utilized the Customary D4 v3 SKU nodepool (16 GB mem, 4 vCPU) in an AKS cluster. The apachebench instrument, generally used for benchmarking and cargo testing net servers, was used for measuring service routing latency. A complete of fifty,000 requests have been generated and measured for total completion time. It has been noticed that the service routing latency of Azure CNI powered by Cilium and kube-proxy initially exhibit comparable efficiency till the variety of pods reaches 5000. Past this threshold, the latency for the service routing for kube-proxy primarily based cluster begins to extend, whereas it maintains a constant latency degree for Cilium primarily based clusters.
Notably, when scaling as much as 16,000 pods, the Azure CNI powered by Cilium cluster demonstrates a big enchancment with a 30 % discount in service routing latency in comparison with the kube-proxy cluster. These outcomes reconfirm that eBPF primarily based service routing performs higher at scale in comparison with IPTables primarily based service routing utilized by kube-proxy.
Service routing latency in seconds
Scale take a look at efficiency
The size take a look at was performed in an Azure CNI powered by Cilium Azure Kubernetes Service cluster, using the Customary D4 v3 SKU nodepool (16 GB mem, 4 vCPU). The aim of the take a look at was to judge the efficiency of the cluster below excessive scale circumstances. The take a look at targeted on capturing the central processing unit (CPU) and reminiscence utilization of the nodes, in addition to monitoring the load on the API server and Cilium.
The take a look at encompassed three distinct eventualities, every designed to evaluate completely different features of the cluster’s efficiency below various circumstances.
Scale take a look at with 100k pods with no community coverage
The size take a look at was executed with a cluster comprising 1k nodes and a complete of 100k pods. The take a look at was performed with none community insurance policies and Kubernetes companies deployed.
Through the scale take a look at, because the variety of pods elevated from 20K to 100K, the CPU utilization of the Cilium agent remained persistently low, not exceeding 100 milli cores and reminiscence is round 500 MiB.
Scale take a look at with 100k pods with 2k community insurance policies
The size take a look at was executed with a cluster comprising 1K nodes and a complete of 100K pods. The take a look at concerned the deployment of 2K community insurance policies however didn’t embrace any Kubernetes companies.
The CPU utilization of the Cilium agent remained below 150 milli cores and reminiscence is round 1 GiB. This demonstrated that Cilium maintained low overhead though the variety of community insurance policies obtained doubled.
Scale take a look at with 1k companies with 60k pods backend and 2k community insurance policies
This take a look at is executed with 1K nodes and 60K pods, accompanied by 2K community insurance policies and 1K companies, every having 60 pods related to it.
The CPU utilization of the Cilium agent remained at round 200 milli cores and reminiscence stays at round 1 GiB. This demonstrates that Cilium continues to take care of low overhead even when massive variety of companies obtained deployed and as we now have seen beforehand service routing by way of eBPF gives important latency beneficial properties for purposes and it’s good to see that’s achieved with very low overhead at infra layer.
Get began with Azure CNI powered by Cilium
To wrap up, as evident from above outcomes, Azure CNI with eBPF dataplane of Cilium is most performant and scales a lot better with nodes, pods, companies, and community insurance policies whereas retaining overhead low. This product providing is now usually out there in Azure Kubernetes Service (AKS) and works with each Overlay and VNET mode for CNI. We’re excited to ask you to attempt Azure CNI powered by Cilium and expertise the advantages in your AKS surroundings.
To get began right this moment, go to the documentation out there on Azure CNI powered by Cilium.