Using BCC and bpftrace with Performance Co-Pilot Andreas Gerstmayr October 28, 2020 Source: https://pcp.io https://github.com/iovisor/bcc https://bpftrace.org 2 eBPF Compiler Collection bpftrace for eBPF Performance Co-Pilot system performance analysis toolkit Performance Co-Pilot 3 Toolkit for collecting, analyzing, visualizing and responding to the status and performance of servers servers, applications and networks. 92 6000+ Agents Performance Metrics Domain Agents export performance data from the kernel, services (e.g. PostgreSQL) and other instrumented applications Metrics

Metrics Example Prometheus & Grafana Deployment Metrics Reference Performance & Scalability Tuning Guide CNI Performance Benchmark Scalability Troubleshooting Component & Cluster Health Observing Flows with DNS name? Why Cilium & Hubble? eBPF is enabling visibility into and control over systems and applications at a granularity and efficiency that was not possible before. It does so in a completely transparent workloads such as virtual machines and standard Linux processes. The development of modern datacenter applications has shifted to a service-oriented architecture often referred to as microservices, wherein a large

Metrics Example Prometheus & Grafana Deployment Metrics Reference Performance & Scalability Tuning Guide CNI Performance Benchmark Scalability Troubleshooting Component & Cluster Health Observing Flows with DNS name? Why Cilium & Hubble? eBPF is enabling visibility into and control over systems and applications at a granularity and efficiency that was not possible before. It does so in a completely transparent workloads such as virtual machines and standard Linux processes. The development of modern datacenter applications has shifted to a service-oriented architecture often referred to as microservices, wherein a large

Metrics Example Prometheus & Grafana Deployment Metrics Reference Scalability Limiting Identity-Relevant Labels Scalability report Performance Evaluation Setup Evaluation Results Tuning Troubleshooting DNS name? Why Cilium & Hubble? BPF is enabling visibility into and control over systems and applications at a granularity and efficiency that was not possible before. It does so in a completely transparent workloads such as virtual machines and standard Linux processes. The development of modern datacenter applications has shifted to a service-oriented architecture often referred to as microservices, wherein a large

Metrics Example Prometheus & Grafana Deployment Metrics Reference Scalability Limiting Identity-Relevant Labels Scalability report Performance Evaluation Setup Evaluation Results Tuning Troubleshooting DNS name? Why Cilium & Hubble? eBPF is enabling visibility into and control over systems and applications at a granularity and efficiency that was not possible before. It does so in a completely transparent workloads such as virtual machines and standard Linux processes. The development of modern datacenter applications has shifted to a service-oriented architecture often referred to as microservices, wherein a large

application code or container configuration. Why Cilium? The development of modern datacenter applications has shifted to a service-oriented architecture often referred to as microservices, wherein a large that communicate with each other via APIs using lightweight protocols like HTTP. Microservices applications tend to be highly dynamic, with individual containers getting started or destroyed as the application how to use it. Secure service to service communication based on identities Modern distributed applications rely on technologies such as application containers to facilitate agility in deployment and scale

application code or container configuration. Why Cilium? The development of modern datacenter applications has shifted to a service-oriented architecture often referred to as microservices, wherein a large that communicate with each other via APIs using lightweight protocols like HTTP. Microservices applications tend to be highly dynamic, with individual containers getting started or destroyed as the application how to use it. Secure service to service communication based on identities Modern distributed applications rely on technologies such as application containers to facilitate agility in deployment and scale

is the cilium-etcd-operator? It is suitable for small and medium scale deployments where etcd performance is not absolutely essen�al. Please refer to the Limita�ons sec�on below to learn about the exact certain scale. The cilium-etcd-operator will not take any measures to provide fast disk access and performance will depend whatever is provided to the pods in your Kubernetes cluster. See etcd Hardware recommenda�ons to set up Cilium on Kubernetes using an external etcd. Use of an external etcd provides be�er performance and is suitable for larger environments. If you are looking for a simple installa�on method to

800) ● Software engineering area with more than 150 engineers Reduce operational complexity Scalability Availability Observability Security Reliability Messaging Analytics Multi-tenancy caveats ○ Infrastructure is operated by a team of 3 engineers ● Reduce costs ● Security issues ● Scalability issues Namespaces +400 Pods +10k Services +3k CPU +2k Mem +5TB Nodes +300 kube-proxy Multi-cluster DNS Aware NetworkPolicy Increased Istio security External Services TLS visibility Performance Kafka policies by labels

Visibility and Auditing ❏ Minimize maintenance and performance overhead ❏ Scale past iptables limits ❏ … 4 Network Security and Auditing 5 Scalability and Maintainability Source: https://commons.wikimedia wikimedia.org/wiki/File:Pictofigo-Scalability.png 6 Evaluating eBPF CNI Offerings 7 8 9 10 Evaluating Cilium and Hubble 11 Cilium Benefits TIP: To change picture:Right click on image > Replace