ers the information edge on the battlefield. Booz Allen is transforming military opera- tions in complex and remote locations with the use of groundbreaking technologies, to enable decision-making at ability to drive a more agile, cloud native and microservices-centric strategy, in solving the most complex of infrastruc- ture management challenges. When it came to Kubernetes management, the team trialed strategies and operate our edge devices in a clustered fashion. It really does support distributed processing across devices.” Ben Reif Lead Developer Booz Allen Hamilton 4 www.susergs.com Advancing the

•���� •��� • ������� • ����� • ���� • ������ • �� • ���� • ��� • ���/� • ������ �� �� Stdout �� Event Journal IoT ��� 100W * 1M = 1TB 100W * 1% = 10000� SAAS ������ ����� LogReduce �������� •���: QuickBI DataV Log Service / Dashboard ��� Stream Processing SparkStreaming Function Compute Hadoop HIVE Big Data Analytics Batch Processing Pig PAI MaxCompute EMR Interactive Analytics DLA Service / Analytics �� Flink Storm ����������� Audit Ingress Mesh Event HPA Kubernetes������ ��� ���� Mesh ���� Stdout �� Event … DaemonSet Sidecar Appender Journal ������� �� ���� ��� ���� ����

1min pod is removed from etcd Unhealthy Node Taint/Degrade 1min Node has taints or is degraded Processing Base on the failure reason Unhealth node is healed or removed. Reason classification: Source ContainerCrashLoopBackOff, FailedPostStartHook, Unhealthy… Trace system Increase of SLO Data Collect Audit log Event The unhealthy node Monitoring Isolation Recover Degrade Data Analysis Failures/Machine Failures/Reason node： Detect the unhealthy machines timely and fix problems automatically。 The infrastructure Log Event End User Storage Analysis Platform Trace Report Weakness The trace system Data Collect: Collect

Registry Private Zone ENI Pod 使用场景 Use cases • Multimedia processing • IoT sensor messages processing • Stream processing at scale • Chat bots • Batch jobs or scheduled tasks • HTTP REST • Mobile backends • Continuous Integration Pipeline • Data Analytics • … Asynchronous Event Driven Stateless High dynamic Short Duration 14 - 一键部署Spark集群 - 无需管理服务器节点 - 灵活弹性，无限扩容

and stop the copy- and-paste madness. • Help you define, install, and upgrade even the most complex Kubernetes application. • Official community： https://helm.sh/ Core concepts in Helm Helm installation. And to find new charts, you can search Helm chart repositories. Apache OpenWhisk Source event Trigger Rule Action Result A serverless, open source cloud platform that executes functions

backups of the Operand • Operator is able to restore a backup of an Operand • Operator orchestrates complex re- configuration flows on the Operand • Operator implements fail-over and fail-back of clustered Controller-runtime 的 Reconcile 过程是一个 EDA 模型，当该 stale 对象的更新到达 cache 时，controller-runtime 会发送一个事件（Event）给到 owner controller（也就是我们的 cluster controller）。这时该对象处于 latest 状态， 根据表格，Plan Action执行后符合预期。对于其它已经处于

Istio Apache Beam TensorFlow Service Communication Management Container Orchestration Data Processing Pipelines Data Flow Graphs for Machine Intelligence Kubernetes Contributors opensource.google 涵蓋Web/App/DB皆有多 樣化代管服務可以組合出 最適架構 自動化部署 與開放平台以及開發環境 整合，加速應用上線 Google Cloud Taiwan 優勢 Google Infrastructure event driven functions web apps & APIs orchestrate containers infrastructure 使用多層次的架構重塑雲端佈署 應用佈建於 IaaS

payload CI/CD Examples - Gitlab/Harbor/Jira Integration Event payload can be passed to build task if needed gitlab new merge request event git log --pretty=oneline c5eff7ea..3211901e 3211901e9b

Scheduler Framework》 The IEEE ISPA 2018 (16th IEEE International Symposium on Parallel and Distributed Processing with Applications) 能力扩展：GPU支持 资源-访问代价树 四类通信方式分类中，通信开销最大的是SOC，其次是PXB，再次是PHB，PIX通信方式 的GPU之间的通信开销最小。 Container Clouds》 The IEEE ISPA 2018 (16th IEEE International Symposium on Parallel and Distributed Processing with Applications) 生态 Next Tencent Kubernetes Engine

和停⽌前处理。具体参⻅ https://kubernetes.io/docs/tasks/configure-pod-container/attach-handler-lifecycle- event/。 启动执⾏：为容器设置预启动命令和参数。 启动后处理：为容器设置启动后的命令。 停⽌前处理：为容器设置预结束命令。 数据卷：⽀持配置本地存储和云存储。 本地存储：⽀持主机⽬录（hos 和停⽌前处理。具体参⻅ https://kubernetes.io/docs/tasks/configure-pod-container/attach-handler-lifecycle- event/。 启动执⾏：为容器设置预启动命令和参数。 启动后处理：为容器设置启动后的命令。 停⽌前处理：为容器设置预结束命令。 数据卷：⽀持配置本地存储和云存储。 本地存储：⽀持主机⽬录（hos