tosca

Autoscaling in reality: Lessons learned from adaptively scaling Kubernetes

Autoscaling in reality: Lessons learned from adaptively scaling Kubernetes

February 29, 2020

Andy Kwiatkowski takes a deep dive into how Shopify saved a million dollars a year in infrastructure costs by rolling its own autoscaler.
About Space Invaders and automated scaling

About Space Invaders and automated scaling

February 22, 2020

Michael Friedrich and Stefanie Grunwald explore how an algorithm capable of playing Space Invaders can also improve your cloud service's automated scaling mechanism.
Downscaling: The Achilles heel of autoscaling Spark clusters

Downscaling: The Achilles heel of autoscaling Spark clusters

February 14, 2020

Autoscaling of resources aims to achieve low latency for a big data application while reducing resource costs. Upscaling a cluster in cloud is fairly easy as compared to downscaling nodes, and so the overall total cost of ownership (TCO) goes up. Prakhar Jain and Sourabh Goyal examine a new design to get efficient downscaling, which helps achieve better resource utilization and lower TCO.
Developing serverless applications on Kubernetes with Knative (sponsored by Pivotal)

Developing serverless applications on Kubernetes with Knative (sponsored by Pivotal)

January 30, 2020

There's too much fragmentation for developers when it comes to deciding the right open source FaaS solution. Bryan Friedman and Brian McClain detail Knative, an open source project from Google, Pivotal, and other industry leaders that provides a set of common tooling on top of Kubernetes to help developers build functions.
Isolate computing

Isolate computing

January 21, 2020

The technology invented for web browsers is a much better way of running serverless code than traditional processes and containers. Let Zack Bloom show you why.
Serverless for data and AI

Serverless for data and AI

January 6, 2020

What is serverless, and how can it be utilized for data analysis and AI? Avner Braverman outlines the benefits and limitations of serverless with respect to data transformation (ETL), AI inference and training, and real-time streaming. This is a technical talk, so expect demos and code.
ONAP Controller Framework Evolution with CDS - Alexis de Talhout &

ONAP Controller Framework Evolution with CDS - Alexis de Talhout &

January 3, 2020

A lot of existing controllers focus on transport, by implementing southbound protocols such as NetConf, OpenFlow, etc…This generic controller also focuses on content, and follow the Inversion of Con …
The TOSCA Datacenter

The TOSCA Datacenter

January 2, 2020

TOSCA has been making inroads into the datacenter and it's high time we asked of it to take us all the way. Originally, it was aimed at deploying on-top-of-the-cloud workloads with the Simple Profile. …
Panel Discussion: Towards Kubernetes as the Network Service Orchestrator

Panel Discussion: Towards Kubernetes as the Network Service Orchestrator

December 29, 2019

In the current landscape, network services are defined by a slow-moving standards ecosystem (TOSCA etc.) with vendor proprietary extensions. With the advent of Edge Computing and 5G, dynamism of Netwo …
A Pathway To Multi-Tenancy in Kubernetes

A Pathway To Multi-Tenancy in Kubernetes

December 25, 2019

Building large, distributed software is not easy, especially when you must support multiple tenants that each have their own workloads to run and SLAs to meet, while compute and storage resources are …
Lightning Talk: Open Match - Matchmaking Framework

Lightning Talk: Open Match - Matchmaking Framework

December 23, 2019

Open Match is an open source game matchmaking framework that simplifies building a scalable and extensible Matchmaker. Open Match is designed to give the game developer full control over how to genera …
Live Aggregators: A scalable, cost-effective, and reliable way of aggregating billions of messages in real time

Live Aggregators: A scalable, cost-effective, and reliable way of aggregating billions of messages in real time

December 23, 2019

Osman Sarood and Chunky Gupta discuss Mists real-time data pipeline, focusing on Live Aggregators (LA)a highly reliable and scalable in-house real-time aggregation system that can autoscale for sudden changes in load. LA is 80% cheaper than competing streaming solutions due to running over AWS Spot Instances and having 70% CPU utilization.
Serverless for data and AI

Serverless for data and AI

December 21, 2019

What is serverless, and how can it be utilized for data analysis and AI? Avner Braverman outlines the benefits and limitations of serverless with respect to data transformation (ETL), AI inference and training, and real-time streaming. This is a technical talk, so expect demos and code.
10 Weird Ways to Blow Up Your Kubernetes

10 Weird Ways to Blow Up Your Kubernetes

December 15, 2019

Its a brand new world in infrastructure with the advent of microservices, containerization, Kubernetes, and service mesh. And all is well. Or is it? Find out how easy it is to break container runtime …
Advanced Model Inferencing Leveraging KNative, Istio and Kubeflow Serving

Advanced Model Inferencing Leveraging KNative, Istio and Kubeflow Serving

December 10, 2019

Model Inferencing use cases are becoming a requirement for models moving into the next phase of production deployments. More and more users are now encountering use cases around canary deployments, sc …
Deep Dive into Autoscaling

Deep Dive into Autoscaling

December 8, 2019

Come and see how to debug and optimize your autoscalers and decrease your monthly infrastructure costs even further. During this talk members of SIG-Autoscaling will discuss the internals of HPA, VPA …
Emitting, Consuming, and Presenting: The Event Lifecycle

Emitting, Consuming, and Presenting: The Event Lifecycle

December 6, 2019

Youre building a suite of operators and processes that will run in your cluster to make your job easier. Youve written CRDs to manage cluster and out of cluster resources, youve set up your monitor …
Serverless Platform for Large Scale Mini-Apps: From Knative to Production

Serverless Platform for Large Scale Mini-Apps: From Knative to Production

November 28, 2019

Serverless architecture is getting increasingly popular. However, developers are still experiencing pain points that hold them back from using it in production, like portability, interoperability and …
KEDA: Event Driven and Serverless Containers in Kubernetes

KEDA: Event Driven and Serverless Containers in Kubernetes

November 26, 2019

Event driven and serverless architectures are defining a new generation of apps. However, to take full advantage of the serverless benefits of event driven, your application needs to scale and react t …
Tutorial: Debug Your Kubernetes Apps

Tutorial: Debug Your Kubernetes Apps

November 26, 2019

Please bring your laptop fully charged as we will have limited charging stations available in the room.Your Kubernetes application is running well, and then all of a sudden the service stops respondin …
Ready to Serve! Speeding-Up Startup Time of Istio-Powered Workloads

Ready to Serve! Speeding-Up Startup Time of Istio-Powered Workloads

November 20, 2019

Pod startup time has long been a focus area for cloud-native platforms. Optimizing startup time is critical to support use cases such as autoscaling, upgrades, and failure recovery. The recent rise of …
Resize Your Pods w/o Disruptions aka How to Have a Cake and Eat a Cake

Resize Your Pods w/o Disruptions aka How to Have a Cake and Eat a Cake

November 5, 2019

Whether youre using Vertical Pod Autoscaler or controlling Pod resources on your own, one thing is certain: applying new settings is disruptive as it requires Pods to be killed and recreated. Why sho …
Deep Dive: Kubernetes Metric APIs Using Prometheus

Deep Dive: Kubernetes Metric APIs Using Prometheus

November 2, 2019

Kubernetes traditionally uses metrics for its core scheduling decisions - in the beginning all of this started with an opinionated internal stack. Since then Kubernetes has introduced 3 orthogonal sta …
Autoscaling Multi-Cluster Observability with Thanos and Linkerd

Autoscaling Multi-Cluster Observability with Thanos and Linkerd

October 25, 2019

Uniform observability across polyglot applications can be challenging, even more so across multiple clusters. In this talk, Andrew Seigner from the Linkerd team and Frederic Branczyk from the Promethe …
Deep Dive: Autoscaling SIG

Deep Dive: Autoscaling SIG

October 18, 2019

Join members of SIG Autoscaling to learn more details about vertical and cluster autoscalers. In this session we will discuss how they work internally, how to check what they are up to and how to debu …
Managing Large-Scale Kubernetes Clusters Effectively and Reliably

Managing Large-Scale Kubernetes Clusters Effectively and Reliably

September 28, 2019

As the business grows, we need to deploy Kubernetets into several data centers all around the world. There are more than ten thousands of Nodes in a single data center. The critical challenge we are f …
Cloud Native Application Monitoring and Autoscaling in Kubernetes

Cloud Native Application Monitoring and Autoscaling in Kubernetes

September 26, 2019

Cloud native means rendering applications the ultimate flexibility, while it is indeed critical to have a thorough insight by monitoring the scaling process.This demo demonstrates the scaling process …