## VMware SIG Deep Dive into Kubernetes Scheduling Performance and high availability options for vSphere Steve Wong, Michael Gasch KubeCon North America December 13, 2018 ## Presenter Bios ## Steve options, for both control plane and worker nodes. 2 levels of scheduling and resource management are active. Currently no automatic scheduling integration occurs, that is, Kubernetes is not aware of the distribution running on the vSphere stack. Kubernetes default scheduling How it works ## Agenda ## Utilizing Zones to improve scheduling Using vSphere tags to define regions and zones – add cloud provider

## +23 ### BehaviorTree.CPP: Task Planning for Robots and Virtual Agents ## DAVIDE FACONTI ## 20 23 October 01 - 06 ## What you will learn today 1. What Behavior Trees are 2. About the C++ library ments/8/d/b/6/8db662e9d441565a9dd326035c73ae34/p7_1.jpg) ## Robot Behaviors This Coordinator or Task Planner is also the highest level of abstraction of our system, where we focus on WHAT the robot does

# 动态资源管理和容器技术 在金融行业的架构探索和明天 ## Resource Scheduling & Container Technology for Financial Service 余军 Gopher China 2015 ## 关于我 ☐ ~19y+ Linux & opensource experience ☐ Co-founder of Shanghai 成时间的主机，不同的是Max-Min算法从所有任务的最小完成时间中选取一个最大值，然后进行相应任务。主机映射，之后重复此过程直至待调度任务集合为空。 ⑥ 轮询调度（Round Robin Scheduling）算法就是以轮询的方式依次将请求调度不同的服务器，即每次调度执行 $ i=(i+1)\mod n $ ，并选出第i台服务器。轮叫调度算法假设所有服务器处理性能均相同，不管服务器的当前连接数和 pick user $i$ with lowest dominant share $s_{i}$ $D_{i} \leftarrow$ demand of user $i$'s next task if $C + D_{i} \leq R$ then $C = C + D_{i}$ ▷ update consumed vector $U_{i} = U_{i} + D_{i}$

## +24 ## Work Contracts Rethinking Task Based Concurrency and Parallelism for Low Latency C++ MICHAEL A MANISCALCO ### “We cannot solve our problems with the same thinking we used when we created them So what is there to Rethink? ## Rethinking: Task Queues  ## Problem #1 - Task Queues Do Not Scale Well: • Contention: ☐ problems: ☐ Task starvation ☐ Load balancing ☐ Forfeits strict FIFO behaviour ○ Increases memory footprint (or requires allocations) ☐ Terrible task selection "fairness" ## Rethinking: Task Queues

the current stable version of Celery (4.0). For development docs, go here. ## Celery - Distributed Task Queue Celery is a simple, flexible, and reliable distributed system to process vast amounts of messages with the tools required to maintain such a system. It’s a task queue with focus on real-time processing, while also supporting task scheduling. Celery has a large and diverse community of users and contributors Getting Started Release: 4.0 Date: Dec 09, 2016 • Introduction to Celery. • What's a Task Queue? • What do I need? • Get Started • Celery is... • Features • Framework

## +23 ## Taro: Task graph-based Asynchronous Programming Using C++ Coroutine DIAN-LUN LIN 20 23 October 01 - 06 ## Agenda • Understand the motivation behind Taro • Learn to use the Taro C++ programming programming model • Dive into the Taro’s coroutine-aware scheduling algorithm • Evaluate Taro on microbenchmarks and a real-world application • Conclusion ## Agenda • Understand the motivation behind model • Dive into the Taro’s coroutine-aware scheduling algorithm • Evaluate Taro on microbenchmarks and a real-world application • Conclusion ## What is Task Graph-based Programming System (TGPS) • TGPS

Inline Resources 87 6.2.2. Creating Email Content by Using a Templating Library 89 7. Task Execution and Scheduling 90 7.1. The Spring TaskExecutor Abstraction 90 7.1.1. TaskExecutor Types 90 7.1 3. TaskScheduler implementations 94 7.3. Annotation Support for Scheduling and Asynchronous Execution 95 7.3.1. Enable Scheduling Annotations 95 7.3.2. The @Scheduled annotation 96 7.3.3. The @Async perform common operations and, for more sophisticated usage, delegate the essence of the processing task to user-implemented callback interfaces. The JMS template follows the same design. The classes offer

pages 38 1.12 Architecture 41 1.13 Examples 43 Python Module Index Django Q is a native Django task queue, scheduler and worker application using Python multiprocessing. ## Features • Multiprocessing queue name. Defaults to 'default'. Note: Tasks are encrypted. When a worker encounters a task it can not decrypt, it will be discarded or failed. #### 1.2.2 workers The number of workers to basis. Defaults to 500. #### 1.2.4 timeout The number of seconds a worker is allowed to spend on a task before it’s terminated. Defaults to None, meaning it will never time out. Set this to something that

pages 38 1.12 Architecture 40 1.13 Examples 42 Python Module Index Django Q is a native Django task queue, scheduler and worker application using Python multiprocessing. ## Features • Multiprocessing queue name. Defaults to 'default'. Note: Tasks are encrypted. When a worker encounters a task it can not decrypt, it will be discarded or failed. #### 1.2.2 workers The number of workers to basis. Defaults to 500. #### 1.2.4 timeout The number of seconds a worker is allowed to spend on a task before it’s terminated. Defaults to None, meaning it will never time out. Set this to something that

actors (2) libprocess (3) revisiting the problem (4) evolution of libprocess (5) eventuals (6) scheduling (7) streams (8) type erasure ## chapters (1) motivating futures/promises + actors (2) libprocess libprocess (3) revisiting the problem (4) evolution of libprocess (5) eventuals (6) scheduling (7) streams (8) type erasure key challenges we’ve faced building distributed systems with good performance actors (2) libprocess (3) revisiting the problem (4) evolution of libprocess (5) eventuals (6) scheduling (7) streams (8) type erasure ## chapters (1) motivating futures/promises + actors (2) libprocess