Make Accelerator Pluggable for Container Engine
•
2 likes•560 views
This document proposes making hardware accelerators like GPUs and FPGAs pluggable for container engines. It discusses identifying accelerator requirements, preparing runtimes, and managing resources. A pluggable accelerator interface is suggested to integrate different plugins for devices like GPUs, DPDK, and FPGAs in a standardized way and manage their lifecycles together with containers. This would allow containers to easily leverage various hardware accelerators.
Report
Share
Report
Share
Download to read offline
Recommended
Quickly Debug VM Failures in OpenStack
This document discusses how to quickly debug VM failures in OpenStack. It begins by explaining where VMs run in OpenStack and how VM startup is implemented. It then describes how to use various logs from OpenStack components like Nova, Neutron, and libvirt/Qemu to troubleshoot issues. The document also provides examples of common VM failure types and outlines steps for debugging, including checking configuration settings, log files, and using troubleshooting tools like Virsh and ABRT. Finally, it calls for collecting VM failure scenarios and solutions to integrate into monitoring tools like StackTach.
64-bit ARM Unikernels on uKVM
This document discusses unikernels and uKVM running on ARM64 architecture. It provides an introduction to unikernels and how they address issues with traditional workloads on the cloud like slow initialization and excessive resource usage. It describes how uKVM provides virtualization for unikernels and the work being done to port uKVM to ARM64. A demo shows the small footprint and fast boot time of an Nginx unikernel running on uKVM for ARM64, and how many instances can run simultaneously on a single host. Future work is outlined to improve compatibility and performance.
Simplify Networking for Containers
Presentation given at the 2017 LinuxCon China
With the booming of Container technology, it brings obvious advantages for cloud: simple and faster deployment, portability and lightweight cost. But the networking challenges are significant. Users need to restructure their network and support container deployment with current cloud framework, like container and VMs.
In this presentation, we will introduce new container networking solution, which provides one management framework to work with different network componenets through Open/friendly modelling mechnism. iCAN can simplify network deployment and management with most orchestration systems and a variety of data plane components, and design extendsible architect to define and validate Service Level Agreement(SLA) for cloud native applications, which is important factor for enterprise to deliver successful and stable service via containers.
OpenNebulaConf 2016 - Measuring and tuning VM performance by Boyan Krosnov, S...
In this session we'll explore measuring VM performance and evaluating changes to settings or infrastructure which can affect performance positively. We'll also share the best current practice for architecture for high performance clouds from our experience.
OpenStack on AArch64
Besides huge success in mobile, ARM is also ambitious in server field. Software ecosystem is now a barrier for wide deployment of ARM servers in data center. ARM Shanghai Workloads team is working on clouding and big data software enablement and optimization on ARM64 platform.
In this presentation, Yibo Cai will introduce the status and challenges of running OpenStack on ARM servers, with emphasis on OpenStack compute, storage and networking.
Rethinking the OS
Presentation delivered at LinuxCon China 2017. Rethinking the Operating System.
A new wave of Operating Systems optimized for containers appeared on the horizon making us excited and puzzeled at the same time.
"Why do we need anything different for containers when traditional OSs served us well in the last 25+ years?" "Isn't Kubernetes just another package to install on top of my favorite distro?"" Will this obsolete my whole infrastructure?" are some of the questions this talk will shed some light on.
Explore the journey SUSE made in rethinking the OS: From a conservative linux distribution to a platform that goes hand in hand with the needs of Microservices.
You will get an insight at what lessons were learned during the intense development effort that lead to SUSE Containers as a Service Platform, how the obstacles along the way were lifted and why "Upstream first" is - and should always be - the rule.
Get a Taste of 1 k+ Nodes by a Handful of Servers
This document discusses containerized testing of OpenStack scalability. It explores using Docker containers to provision OpenStack components like Neutron and OpenDaylight in a distributed manner. The approach aims to test scalability up to 1,000 nodes using a handful of physical servers. It analyzes component footprints and tasks. Considerations for extending the tests to larger 1,000 node scales include physical server capacity, container placement density, network bandwidth, and more sophisticated test scenarios.
Releasing a Distribution in the Age of DevOps.
Presentation delivered at LinuxCon China 2017.
Operating systems need to move faster without sacrificing stability. New hardware, new software features, and bugfixes are making it into distribution components every day. To maintain stability, packagers and distribution developers are looking toward lessons learned in the DevOps movement to implement Continuous Integration/Continuous Delivery (CI/CD) workflows that provide quicker test feedback to developers.
This talk highlights some of the coming trends in Fedora such as: streamlined base package sets, userspace applications delivered as containers, continuous validation of individual distro components and the distro as a whole, and collaboration with the CentOS Project.
Recommended
Quickly Debug VM Failures in OpenStack
This document discusses how to quickly debug VM failures in OpenStack. It begins by explaining where VMs run in OpenStack and how VM startup is implemented. It then describes how to use various logs from OpenStack components like Nova, Neutron, and libvirt/Qemu to troubleshoot issues. The document also provides examples of common VM failure types and outlines steps for debugging, including checking configuration settings, log files, and using troubleshooting tools like Virsh and ABRT. Finally, it calls for collecting VM failure scenarios and solutions to integrate into monitoring tools like StackTach.
64-bit ARM Unikernels on uKVM
This document discusses unikernels and uKVM running on ARM64 architecture. It provides an introduction to unikernels and how they address issues with traditional workloads on the cloud like slow initialization and excessive resource usage. It describes how uKVM provides virtualization for unikernels and the work being done to port uKVM to ARM64. A demo shows the small footprint and fast boot time of an Nginx unikernel running on uKVM for ARM64, and how many instances can run simultaneously on a single host. Future work is outlined to improve compatibility and performance.
Simplify Networking for Containers
Presentation given at the 2017 LinuxCon China
With the booming of Container technology, it brings obvious advantages for cloud: simple and faster deployment, portability and lightweight cost. But the networking challenges are significant. Users need to restructure their network and support container deployment with current cloud framework, like container and VMs.
In this presentation, we will introduce new container networking solution, which provides one management framework to work with different network componenets through Open/friendly modelling mechnism. iCAN can simplify network deployment and management with most orchestration systems and a variety of data plane components, and design extendsible architect to define and validate Service Level Agreement(SLA) for cloud native applications, which is important factor for enterprise to deliver successful and stable service via containers.
OpenNebulaConf 2016 - Measuring and tuning VM performance by Boyan Krosnov, S...
In this session we'll explore measuring VM performance and evaluating changes to settings or infrastructure which can affect performance positively. We'll also share the best current practice for architecture for high performance clouds from our experience.
OpenStack on AArch64
Besides huge success in mobile, ARM is also ambitious in server field. Software ecosystem is now a barrier for wide deployment of ARM servers in data center. ARM Shanghai Workloads team is working on clouding and big data software enablement and optimization on ARM64 platform.
In this presentation, Yibo Cai will introduce the status and challenges of running OpenStack on ARM servers, with emphasis on OpenStack compute, storage and networking.
Rethinking the OS
Presentation delivered at LinuxCon China 2017. Rethinking the Operating System.
A new wave of Operating Systems optimized for containers appeared on the horizon making us excited and puzzeled at the same time.
"Why do we need anything different for containers when traditional OSs served us well in the last 25+ years?" "Isn't Kubernetes just another package to install on top of my favorite distro?"" Will this obsolete my whole infrastructure?" are some of the questions this talk will shed some light on.
Explore the journey SUSE made in rethinking the OS: From a conservative linux distribution to a platform that goes hand in hand with the needs of Microservices.
You will get an insight at what lessons were learned during the intense development effort that lead to SUSE Containers as a Service Platform, how the obstacles along the way were lifted and why "Upstream first" is - and should always be - the rule.
Get a Taste of 1 k+ Nodes by a Handful of Servers
This document discusses containerized testing of OpenStack scalability. It explores using Docker containers to provision OpenStack components like Neutron and OpenDaylight in a distributed manner. The approach aims to test scalability up to 1,000 nodes using a handful of physical servers. It analyzes component footprints and tasks. Considerations for extending the tests to larger 1,000 node scales include physical server capacity, container placement density, network bandwidth, and more sophisticated test scenarios.
Releasing a Distribution in the Age of DevOps.
Presentation delivered at LinuxCon China 2017.
Operating systems need to move faster without sacrificing stability. New hardware, new software features, and bugfixes are making it into distribution components every day. To maintain stability, packagers and distribution developers are looking toward lessons learned in the DevOps movement to implement Continuous Integration/Continuous Delivery (CI/CD) workflows that provide quicker test feedback to developers.
This talk highlights some of the coming trends in Fedora such as: streamlined base package sets, userspace applications delivered as containers, continuous validation of individual distro components and the distro as a whole, and collaboration with the CentOS Project.
[20200720]cloud native develoment - Nelson Lin
There is no shortage now of development and CI/CD tools for cloud-native application development. But how do we put the cloud-native concept and think as the cloud-native way on the leftmost side of CI/CD pipeline.
During developing phrase, the tools provided with cloud code can help you expedite iteration of source codes, run and debug cloud native applications in an easy and fast way, making cloud-native development turn into real-time process, reduce the gap between deployment and development.
現在不乏用於雲原生應用程序開發的開發和 CI/CD工具。 但是，我們如何將雲原生概念放在的 CI/CD 流水線的最左側呢？
在開發階段，如何用 Cloud code 協助您加快原始碼的迭代速度，以簡便快捷的方式運行和調用雲原生應用程序，使雲原生開發變為即使過程，縮小開發與部署之間的差
OCI Support in Mesos
The document discusses support for Open Container Initiative (OCI) images in Mesos. It provides an overview of OCI specifications including the image format specification. It describes how Mesos stores and retrieves OCI images from a default location based on the image layout. It also discusses how the existing Docker isolator was extended to support running containers from both Docker images and OCI images.
Containers for the Enterprise: Delivering OpenShift on OpenStack for Performa...
Imagine being able to stand up thousands of tenants with thousands of apps, running thousands of Docker-formatted container images and routes, all on a self-healing cluster. Now, take that one step further with all of those images being updatable through a single upload to the registry, and with zero downtime. In this session, Steve Gordon of the Red Hat OpenStack Platform team will show you just that. Steve will walk through a recent benchmarking deployment using the Cloud Native Computing Foundation’s (CNCF) new 1,000 node cluster with OpenStack and Red Hat’s OpenShift Container Platform, the enterprise-ready Kubernetes for developers.
Scale Kubernetes to support 50000 services
Kubernetes currently has two load balancing mode: userspace and IPTables. They both have limitation on scalability and performance. We introduced IPVS as third kube-proxy mode which scales kubernetes load balancer to support 50,000 services. Beyond that, control plane needs to be optimized in order to deploy 50,000 services. We will introduce alternative solutions and our prototypes with detailed performance data.
Introduction to CNI (Container Network Interface)
A brief introduction to the CNI (Container Network Interface), the implementation of docker bridge network and the CNI usage, including why we develop the CNI, how to use the CNI and what is CNI.
We also introduction the pause container the kubernetes PoD and how to use the CNI in the kubernetes.
In the end, we use the flannel as an example to show how to install the CNI into your kubernetes cluster
Running Legacy Applications with Containers
Enterprise data centers have to support a diverse of set of workloads: cloud native, big data, high performance computing, and legacy applications. While cloud native applications are ideal to run in Docker clusters, bare metal and virtualization infrastructures must still be supported in the data center. The result is a proliferation of clusters and technologies running in individual silos, resulting in high management costs and low utilization. This talk describes the challenges and experiences in implementing a shared cluster infrastructure based on Kubernetes to support big data, high performance computing, and VM-based workloads. The talk will show the deployment and scaling of a high performance computing workload manager, Spark, and OpenStack, and how the VM and Docker management can be integrated together.
OpenNebulaConf 2016 - OpenNebula, a story about flexibility and technological...
Cloud providers are constantly addressing the technology limitations on their infrastructures, which must be overcome to meet customer needs. On this presentation, we will demonstrate how technological agnosticism and management flexibility of OpenNebula has allowed Todoencloud to provide the most efficient open source solution to the needs of its customers, choosing the most appropriate virtualization technology (Xen and KVM), storage approach (ZFS vs CEPH), Cloud Bursting solutions (Azure, Amazon) and customized networking topologies.
Unikernelized Linux
Presentation given at the 2017 LinuxCon China
Unikernel is a novel software technology that links an application with OS in the form of a library and packages them into a specialized image that facilitates direct deployment on a hypervisor. Comparing to the traditional VM or the recent containers, Unikernels are smaller, more secure and efficient, making them ideal for cloud environments. There are already lots of open source projects like OSv, Rumprun and so on. But why these existing unikernels have yet to gain large popularity broadly? We think Unikernels are facing three major challenges: 1. Compatibility with existing applications; 2. Lack of production support (e.g. monitoring, debugging, logging); 3. Lack of compelling use case. In this presentation, we will review our investigations and exploration of if-how we can convert Linux as Unikernel to eliminate these significant shortcomings, plus some explorations of coordinating and cooperating with hypervisor.
Linuxcon secureefficientcontainerimagemanagementharbor
This document discusses container image management in enterprises and introduces Project Harbor, an open source container registry. It covers key topics like container image basics, Project Harbor features, maintaining consistency of images between environments, security and access control of images, image distribution strategies, and high availability of container registries. Project Harbor provides an enterprise-grade private registry with features for user management, image replication, security, and integration with systems like LDAP. It aims to help organizations securely manage the distribution and storage of container images.
Kubernetes 1001
In this slide, I briefly introduce the container and how docker implement it, including the image and container itself. also show how docker setup the networking connectivity by default bridge network.
OpenNebulaConf 2016 - Budgeting: the Ugly Duckling of Cloud computing? by Mat...
This document discusses budgeting for cloud computing resources at the Leibniz Supercomputing Centre. It provides an introduction and outline, describes the LRZ's compute cloud setup and increasing user base. It proposes a cost function for budgeting based on resources like cores, RAM, and storage space. The document outlines plans for budgeting including hardware classes, user classes, and pre-paid models to avoid budget overflows. It describes the current budgeting implementation and next steps to update OpenNebula and focus on security.
Containerize ovs ovn components
The document discusses containerizing OVS/OVN components to make them easier to manage, move around, and run on Kubernetes. Containerizing them optimizes development efforts by removing the need for kernel modules in OVN and not tying OVN container components to the host OS. It also allows running OVS/OVN as pods in Kubernetes through combining multiple containers in the same pod. The document demonstrates building, pushing and using containerized OVS/OVN and references next steps like running the OVN control plane in a container cluster mode with SSL support.
OpenNebula Conf 2014: CentOS, QA an OpenNebula - Christoph Galuschka
CentOS, the Community Enterprise OS, uses Opennebula as virtualization plattform for its automated QA-process. The opennebula setup consists of 3 nodes, all running CentOS-6, who handle the following tasks:
– sunstone as cloud controller
– local mirror/DNS-Server/http-Server for the VMs to pull in packages
– one VM to run a jenkins instance to launch the various tests (ci.de.centos.org)
– nginx on the cloud controller to forward http traffic to the jenkins VM
A public git repository (http://www.gitorious.org/testautomation) is used to allow whoever wants to contribute to pull the current test suite – t_functional, a series of bash scripts used to do funtional tests of various applications, binaries, configuration files and Trademark issues. As new tests are added to the repo via personal clones and merge requests, those tests first need to complete a test run via jenkins. Each test run currently consists of 4 VMs (one for each arch for C5 and C6 – C7 to come), which run the complete test suite. All VMs used for theses tests are instantiated and torn down on demand, whenever the call to testrun a personal clone is issued (via IRC).
Once completed successfully, the request is merged into the main repo. The jenkins node monitors this repository and which automatically triggers another complete test run.
Besides these triggered test runs, the test suite is automatically triggered daily to run. This is used to verify functionality of published updates – a handfull of failty updates have allready been discovered this way.
Besides t_functional, the Linux Test Project Suite of tests is also run on a daily basis, also to verify functionality of the OS and all updates.
The third setup is used to test the available and functional integrity of published docker images for CentOS.
All these tests are later – during the QA-phase of a point release – used to verify functionality of new packages inside the CentOS QA-Setup.
Application-Based Routing
This talks shows how to implement the Application-Based Routing in the common Linux Distribution. We use the NDPI to execute the DPI function to category the packet first, use the linux kernel build-it mark to pass the information from user-space to kernel space and then the policy routing system use that mark to route the packet by different destination or interface.
DCSF 19 Online Feature Extraction and Event Generation for Computer-Animal In...
This talk will present an architecture developed to investigate the interaction with and between animals. The architecture allows online processing of multimedia streams and the generation, storing and visualizing of events using feature extraction. It allows biologists to analyze the events by monitoring live or by replaying streams through a web interface Docker swarm is the central component of the architecture and serves as infrastructure for stream processing, event generation, event processing and visualization. The main entry point for users is a web interface that spins up one container per user and allows independent replay of streams. This talk will focus on the architecture and on technical details concerning its implementation as well as how docker is utilized to process, store and visualize events. Some time will be spent explaining details about custom made docker solutions.
Leveraging the Power of containerd Events - Evan Hazlett
containerd provides the low-level functionality that enables the Docker Engine to run containers. containerd events provide a simple, yet powerful mechanism to integrate with virtually any other system with minimal effort. This talk will cover what containerd events are and how to use them for integration with systems ranging from monitoring and logging to container networking using CNI (Container Network Interface) plugins.
Container Orchestration from Theory to Practice
Join Laura Frank and Stephen Day as they explain and examine technical concepts behind container orchestration systems, like distributed consensus, object models, and node topology. These concepts build the foundation of every modern orchestration system, and each technical explanation will be illustrated using Docker’s SwarmKit as a real-world example. Gain a deeper understanding of how orchestration systems like SwarmKit work in practice and walk away with more insights into your production applications.
OpenShift v3 Internal networking details
OpenShift v3 uses an overlay VXLAN network to connect pods within a project. Traffic between pods on a node uses Linux bridges, while inter-node communication uses the VXLAN overlay network. Services are exposed using a service IP and iptables rules to redirect traffic to backend pods. For external access, services are associated with router pods using a DNS name, and traffic is load balanced to backend pods by HAProxy in the router pod.
Virtualization inside kubernetes
Containers provide isolation between processes using cgroups and namespaces to limit resource utilization and isolate processes. Containers run within a single operating system kernel and share the kernel with other containers, using fewer resources than virtual machines which run entire guest operating systems. Docker is the most common container platform and uses containerization to package applications and their dependencies into portable containers that can be run on any Linux server.
Linux Kernel Development
Presentation delivered at LinuxCon China 2017 by Greg Kroah-Hartman.
The Linux kernel is the largest collaborative software development projects ever. This talk will discuss exactly how Linux is developed, how fast it is happening, who is doing the work, and how we all stay sane keeping up with it. It will discuss the development model used, and how it differs from almost all "traditional" models of software development.
From Resilient to Antifragile Chaos Engineering Primer
Failure injection is somewhat analogous to a vaccine. We want to inject these bad behaviours so our developers can build immunities to them. Can we inject failure scenarios into deployed systems to reduce platform risk Demonstrations of the Simian Army, Chaos Lemur and Locust.io tools will be presented.
Even when all of the individual services in a distributed system are functioning properly, the interactions between those services can cause unpredictable outcomes. Unpredictable outcomes, compounded by rare but disruptive real-world events that affect production environments, make these distributed systems inherently chaotic.
Secure Containers with EPT Isolation
Secure Container solution is to enhance container security by isolating memory between Docker containers inside one VM with Intel VT-x EPT HW, which is highly effective to protect container’s memory and at the meantime defends ret2user privilege escalation attack that exploits kernel vulnerabilities (eg. CVE-2017-6074 UAF (use-after-free) vulnerability). It extends KVM interfaces which the guest OS can leverage to isolate container memory from other containers, and the interfaces rely on Intel VT-x EPT hardware extension and provide memory access protection for the container which sits in an isolated memory region. Each secure container has a dedicated EPT table rather than sharing one EPT table with guest OS, which enforces the cross-EPT memory access protection. The whole solution is user-friendly to fit in the existing cloud server infrastructure with very limited changes.
More Related Content
What's hot
[20200720]cloud native develoment - Nelson Lin
There is no shortage now of development and CI/CD tools for cloud-native application development. But how do we put the cloud-native concept and think as the cloud-native way on the leftmost side of CI/CD pipeline.
During developing phrase, the tools provided with cloud code can help you expedite iteration of source codes, run and debug cloud native applications in an easy and fast way, making cloud-native development turn into real-time process, reduce the gap between deployment and development.
現在不乏用於雲原生應用程序開發的開發和 CI/CD工具。 但是，我們如何將雲原生概念放在的 CI/CD 流水線的最左側呢？
在開發階段，如何用 Cloud code 協助您加快原始碼的迭代速度，以簡便快捷的方式運行和調用雲原生應用程序，使雲原生開發變為即使過程，縮小開發與部署之間的差
OCI Support in Mesos
The document discusses support for Open Container Initiative (OCI) images in Mesos. It provides an overview of OCI specifications including the image format specification. It describes how Mesos stores and retrieves OCI images from a default location based on the image layout. It also discusses how the existing Docker isolator was extended to support running containers from both Docker images and OCI images.
Containers for the Enterprise: Delivering OpenShift on OpenStack for Performa...
Imagine being able to stand up thousands of tenants with thousands of apps, running thousands of Docker-formatted container images and routes, all on a self-healing cluster. Now, take that one step further with all of those images being updatable through a single upload to the registry, and with zero downtime. In this session, Steve Gordon of the Red Hat OpenStack Platform team will show you just that. Steve will walk through a recent benchmarking deployment using the Cloud Native Computing Foundation’s (CNCF) new 1,000 node cluster with OpenStack and Red Hat’s OpenShift Container Platform, the enterprise-ready Kubernetes for developers.
Scale Kubernetes to support 50000 services
Kubernetes currently has two load balancing mode: userspace and IPTables. They both have limitation on scalability and performance. We introduced IPVS as third kube-proxy mode which scales kubernetes load balancer to support 50,000 services. Beyond that, control plane needs to be optimized in order to deploy 50,000 services. We will introduce alternative solutions and our prototypes with detailed performance data.
Introduction to CNI (Container Network Interface)
A brief introduction to the CNI (Container Network Interface), the implementation of docker bridge network and the CNI usage, including why we develop the CNI, how to use the CNI and what is CNI.
We also introduction the pause container the kubernetes PoD and how to use the CNI in the kubernetes.
In the end, we use the flannel as an example to show how to install the CNI into your kubernetes cluster
Running Legacy Applications with Containers
Enterprise data centers have to support a diverse of set of workloads: cloud native, big data, high performance computing, and legacy applications. While cloud native applications are ideal to run in Docker clusters, bare metal and virtualization infrastructures must still be supported in the data center. The result is a proliferation of clusters and technologies running in individual silos, resulting in high management costs and low utilization. This talk describes the challenges and experiences in implementing a shared cluster infrastructure based on Kubernetes to support big data, high performance computing, and VM-based workloads. The talk will show the deployment and scaling of a high performance computing workload manager, Spark, and OpenStack, and how the VM and Docker management can be integrated together.
OpenNebulaConf 2016 - OpenNebula, a story about flexibility and technological...
Cloud providers are constantly addressing the technology limitations on their infrastructures, which must be overcome to meet customer needs. On this presentation, we will demonstrate how technological agnosticism and management flexibility of OpenNebula has allowed Todoencloud to provide the most efficient open source solution to the needs of its customers, choosing the most appropriate virtualization technology (Xen and KVM), storage approach (ZFS vs CEPH), Cloud Bursting solutions (Azure, Amazon) and customized networking topologies.
Unikernelized Linux
Presentation given at the 2017 LinuxCon China
Unikernel is a novel software technology that links an application with OS in the form of a library and packages them into a specialized image that facilitates direct deployment on a hypervisor. Comparing to the traditional VM or the recent containers, Unikernels are smaller, more secure and efficient, making them ideal for cloud environments. There are already lots of open source projects like OSv, Rumprun and so on. But why these existing unikernels have yet to gain large popularity broadly? We think Unikernels are facing three major challenges: 1. Compatibility with existing applications; 2. Lack of production support (e.g. monitoring, debugging, logging); 3. Lack of compelling use case. In this presentation, we will review our investigations and exploration of if-how we can convert Linux as Unikernel to eliminate these significant shortcomings, plus some explorations of coordinating and cooperating with hypervisor.
Linuxcon secureefficientcontainerimagemanagementharbor
This document discusses container image management in enterprises and introduces Project Harbor, an open source container registry. It covers key topics like container image basics, Project Harbor features, maintaining consistency of images between environments, security and access control of images, image distribution strategies, and high availability of container registries. Project Harbor provides an enterprise-grade private registry with features for user management, image replication, security, and integration with systems like LDAP. It aims to help organizations securely manage the distribution and storage of container images.
Kubernetes 1001
In this slide, I briefly introduce the container and how docker implement it, including the image and container itself. also show how docker setup the networking connectivity by default bridge network.
OpenNebulaConf 2016 - Budgeting: the Ugly Duckling of Cloud computing? by Mat...
This document discusses budgeting for cloud computing resources at the Leibniz Supercomputing Centre. It provides an introduction and outline, describes the LRZ's compute cloud setup and increasing user base. It proposes a cost function for budgeting based on resources like cores, RAM, and storage space. The document outlines plans for budgeting including hardware classes, user classes, and pre-paid models to avoid budget overflows. It describes the current budgeting implementation and next steps to update OpenNebula and focus on security.
Containerize ovs ovn components
The document discusses containerizing OVS/OVN components to make them easier to manage, move around, and run on Kubernetes. Containerizing them optimizes development efforts by removing the need for kernel modules in OVN and not tying OVN container components to the host OS. It also allows running OVS/OVN as pods in Kubernetes through combining multiple containers in the same pod. The document demonstrates building, pushing and using containerized OVS/OVN and references next steps like running the OVN control plane in a container cluster mode with SSL support.
OpenNebula Conf 2014: CentOS, QA an OpenNebula - Christoph Galuschka
CentOS, the Community Enterprise OS, uses Opennebula as virtualization plattform for its automated QA-process. The opennebula setup consists of 3 nodes, all running CentOS-6, who handle the following tasks:
– sunstone as cloud controller
– local mirror/DNS-Server/http-Server for the VMs to pull in packages
– one VM to run a jenkins instance to launch the various tests (ci.de.centos.org)
– nginx on the cloud controller to forward http traffic to the jenkins VM
A public git repository (http://www.gitorious.org/testautomation) is used to allow whoever wants to contribute to pull the current test suite – t_functional, a series of bash scripts used to do funtional tests of various applications, binaries, configuration files and Trademark issues. As new tests are added to the repo via personal clones and merge requests, those tests first need to complete a test run via jenkins. Each test run currently consists of 4 VMs (one for each arch for C5 and C6 – C7 to come), which run the complete test suite. All VMs used for theses tests are instantiated and torn down on demand, whenever the call to testrun a personal clone is issued (via IRC).
Once completed successfully, the request is merged into the main repo. The jenkins node monitors this repository and which automatically triggers another complete test run.
Besides these triggered test runs, the test suite is automatically triggered daily to run. This is used to verify functionality of published updates – a handfull of failty updates have allready been discovered this way.
Besides t_functional, the Linux Test Project Suite of tests is also run on a daily basis, also to verify functionality of the OS and all updates.
The third setup is used to test the available and functional integrity of published docker images for CentOS.
All these tests are later – during the QA-phase of a point release – used to verify functionality of new packages inside the CentOS QA-Setup.
Application-Based Routing
This talks shows how to implement the Application-Based Routing in the common Linux Distribution. We use the NDPI to execute the DPI function to category the packet first, use the linux kernel build-it mark to pass the information from user-space to kernel space and then the policy routing system use that mark to route the packet by different destination or interface.
DCSF 19 Online Feature Extraction and Event Generation for Computer-Animal In...
This talk will present an architecture developed to investigate the interaction with and between animals. The architecture allows online processing of multimedia streams and the generation, storing and visualizing of events using feature extraction. It allows biologists to analyze the events by monitoring live or by replaying streams through a web interface Docker swarm is the central component of the architecture and serves as infrastructure for stream processing, event generation, event processing and visualization. The main entry point for users is a web interface that spins up one container per user and allows independent replay of streams. This talk will focus on the architecture and on technical details concerning its implementation as well as how docker is utilized to process, store and visualize events. Some time will be spent explaining details about custom made docker solutions.
Leveraging the Power of containerd Events - Evan Hazlett
containerd provides the low-level functionality that enables the Docker Engine to run containers. containerd events provide a simple, yet powerful mechanism to integrate with virtually any other system with minimal effort. This talk will cover what containerd events are and how to use them for integration with systems ranging from monitoring and logging to container networking using CNI (Container Network Interface) plugins.
Container Orchestration from Theory to Practice
Join Laura Frank and Stephen Day as they explain and examine technical concepts behind container orchestration systems, like distributed consensus, object models, and node topology. These concepts build the foundation of every modern orchestration system, and each technical explanation will be illustrated using Docker’s SwarmKit as a real-world example. Gain a deeper understanding of how orchestration systems like SwarmKit work in practice and walk away with more insights into your production applications.
OpenShift v3 Internal networking details
OpenShift v3 uses an overlay VXLAN network to connect pods within a project. Traffic between pods on a node uses Linux bridges, while inter-node communication uses the VXLAN overlay network. Services are exposed using a service IP and iptables rules to redirect traffic to backend pods. For external access, services are associated with router pods using a DNS name, and traffic is load balanced to backend pods by HAProxy in the router pod.
Virtualization inside kubernetes
Containers provide isolation between processes using cgroups and namespaces to limit resource utilization and isolate processes. Containers run within a single operating system kernel and share the kernel with other containers, using fewer resources than virtual machines which run entire guest operating systems. Docker is the most common container platform and uses containerization to package applications and their dependencies into portable containers that can be run on any Linux server.
Linux Kernel Development
Presentation delivered at LinuxCon China 2017 by Greg Kroah-Hartman.
The Linux kernel is the largest collaborative software development projects ever. This talk will discuss exactly how Linux is developed, how fast it is happening, who is doing the work, and how we all stay sane keeping up with it. It will discuss the development model used, and how it differs from almost all "traditional" models of software development.
What's hot (20)
Containers for the Enterprise: Delivering OpenShift on OpenStack for Performa...
Containers for the Enterprise: Delivering OpenShift on OpenStack for Performa...
OpenNebulaConf 2016 - OpenNebula, a story about flexibility and technological...
OpenNebulaConf 2016 - OpenNebula, a story about flexibility and technological...
Linuxcon secureefficientcontainerimagemanagementharbor
Linuxcon secureefficientcontainerimagemanagementharbor
OpenNebulaConf 2016 - Budgeting: the Ugly Duckling of Cloud computing? by Mat...
OpenNebulaConf 2016 - Budgeting: the Ugly Duckling of Cloud computing? by Mat...
OpenNebula Conf 2014: CentOS, QA an OpenNebula - Christoph Galuschka
OpenNebula Conf 2014: CentOS, QA an OpenNebula - Christoph Galuschka
DCSF 19 Online Feature Extraction and Event Generation for Computer-Animal In...
DCSF 19 Online Feature Extraction and Event Generation for Computer-Animal In...
Leveraging the Power of containerd Events - Evan Hazlett
Leveraging the Power of containerd Events - Evan Hazlett
Viewers also liked
From Resilient to Antifragile Chaos Engineering Primer
Failure injection is somewhat analogous to a vaccine. We want to inject these bad behaviours so our developers can build immunities to them. Can we inject failure scenarios into deployed systems to reduce platform risk Demonstrations of the Simian Army, Chaos Lemur and Locust.io tools will be presented.
Even when all of the individual services in a distributed system are functioning properly, the interactions between those services can cause unpredictable outcomes. Unpredictable outcomes, compounded by rare but disruptive real-world events that affect production environments, make these distributed systems inherently chaotic.
Secure Containers with EPT Isolation
Secure Container solution is to enhance container security by isolating memory between Docker containers inside one VM with Intel VT-x EPT HW, which is highly effective to protect container’s memory and at the meantime defends ret2user privilege escalation attack that exploits kernel vulnerabilities (eg. CVE-2017-6074 UAF (use-after-free) vulnerability). It extends KVM interfaces which the guest OS can leverage to isolate container memory from other containers, and the interfaces rely on Intel VT-x EPT hardware extension and provide memory access protection for the container which sits in an isolated memory region. Each secure container has a dedicated EPT table rather than sharing one EPT table with guest OS, which enforces the cross-EPT memory access protection. The whole solution is user-friendly to fit in the existing cloud server infrastructure with very limited changes.
Open Source Software Business Models Redux
The document discusses open source software business models and community practices. It describes how software sharing has occurred since the 1940s through organizations like IBM SHARE and MIT's Project Athena. It notes that writing good software is hard work and companies shared software before the Open Source Definition. The document also discusses how open source projects and communities evolve from individual committers to broader ecosystems including users, developers, products, and services. It emphasizes that open source is about engineering economics and gives Red Hat as an example of a company focused on customer success through open source. Finally, it outlines various community practices that can help projects and software mature.
Rebuild - Simplifying Embedded and IoT Development Using Linux Containers
Rebuild - Simplifying Embedded and IoT Development Using Linux ContainersLinuxCon ContainerCon CloudOpen China
This document introduces Rebuild, a tool that uses Linux containers to provide isolated development environments. It allows developers to easily create, modify, run, and share consistent environments. Rebuild provides a CLI to manage environments locally and publish them to remote registries for sharing. Environments can be created from base images on DockerHub or by importing file systems. Rebuild aims to simplify embedded and IoT development by eliminating issues caused by inconsistent environments.GPU Acceleration for Containers on Intel Processor Graphics
Presentation delivered at the 2017 LinuxCon China.
Container is a popular technology in cloud with the merits of fast provisioning, high density and near-native performance. New requirements have been rising to further use GPU to accelerate various applications in containers, e.g. media trans-coding, machine learning, etc. However there is still gap of managing GPU in such container usages. This presentation will first review the status of GPU support on both native container and Intel clear container, then provide an anatomy of technical gaps and enabling plans in major areas (orchestration layer, resource isolation and QoS performance isolation), then review our work for GPU virtualization in clear container and prototype work through extensions in docker plugin, cgroup and GPU scheduler to fix those gaps.
Status of Embedded Linux
This document provides a summary of the status of embedded Linux. It discusses recent Linux kernel versions from 4.7 to the upcoming 4.12, highlighting new features. It also covers technology areas like boot time, device tree, graphics, file systems, and security. Several ongoing Linux Foundation projects are mentioned like Long Term Support Initiative, Fuego test framework, and the eLinux wiki. Finally, it lists upcoming conferences and trade associations working on embedded Linux. The document aims to give a quick overview of the current state of embedded Linux topics and projects.
Libvirt API Certification
This document discusses the architecture and evolution of Libvirt, an open source software library that provides a standardized interface to various virtualization technologies like Xen, QEMU, KVM, LXC, and others. It outlines Libvirt's public API, driver API, and driver implementations that allow applications to manage virtual machines across different platforms. The document also mentions Libvirt's certification process for hardware and software compatibility and its automated testing framework.
LiteOS
The document discusses Internet of Things (IoT) technologies and applications. It describes how Huawei's LiteOS operating system enables device intelligence and easy connectivity between devices and IoT platforms. LiteOS supports a variety of microcontroller boards and has partnered with STMicroelectronics to launch NB-IoT development kits. The document encourages developers to get involved with the LiteOS open source community through its website, GitHub repository, workshops, and other resources.
High Performance Linux Virtual Machine on Microsoft Azure: SR-IOV Networking ...
High Performance Linux Virtual Machine on Microsoft Azure: SR-IOV Networking ...LinuxCon ContainerCon CloudOpen China
Can we leverage the resource of public cloud for gaming, streaming, transcoding, machine learning and visualized CAD application on demand? Yes if it provides the capability and infrastructure to utilize GPUs. Can we get high performance networking in the cloud as what I have in the bare metal environment? Yes with SR-IOV. How to achieve them? In this presentation we describe Discrete Device Assignment (also known as PCI Pass-through) support for GPU and network adapter in Linux guest and SR-IOV architectures of Linux guest with near-native performance profile running on Hyper-V. We also will share how to integrate accelerated graphics and networking capabilities in Microsoft Azure infrastructure. kdump: usage and_internals
Kdump is a long existing method for acquiring dump of crashed kernel, however very few literatures are available to understand it's usage and internals. We receive a lot of queries on kexec mailing list about different issues related to the kexec/kdump environment.
In this presentation, we talk about basics of kdump usage and some internals about kdump/kexec kernel implementation. It includes end to end flow from kdump kernel configuration to crash analysis. We discuss some of the problem which is frequently faced by kdump users. It also includes related information about ELF structure, so that one can debug if vmcore itself gets corrupted because of any architecture related issue.
Practical CNI
The document provides an overview of Container Network Interface (CNI) which is a standard for configuring network interfaces for Linux containers. It discusses how CNI uses plugins to configure networking for containers and provides examples of plugins like ptp, bridge, and IPvlan. It also covers overlay networking techniques like VXLAN and OVN which can be used to provide networking between containers on different hosts.
点融网区块链即服务实践 - The Practice of Blockchain as a Service in Dianrong
点融网区块链即服务实践 - The Practice of Blockchain as a Service in DianrongLinuxCon ContainerCon CloudOpen China
Presentation delivered at LinuxCon China 2017
The practices of Blockchain as a service in Dianrong (Shiyuan Xiao, Dianrong.com) - Blockchain as a Service (BaaS) provides a easy, low-cost and flexible platform for companies to enable their businesses based on blockchain backed by a cloud platform. Shiyuan will introduce the experiences to build such a BaaS platform, what is the architecture, what problems we have met and solved and the best practices we summarized. See what happened with real time kvm when building real time cloud pezhang@re...
See what happened with real time kvm when building real time cloud pezhang@re...LinuxCon ContainerCon CloudOpen China
Presentation delivered at LinuxCon China 2017
Real-Time is used for deadline-oriented applications and time-sensitive workloads. Real-Time KVM is the extension of KVM(Linux Kernel-based Virtual Machine) to allow the virtual machines(VM) to be a truly Real-Time operating system.Users sometimes need to run low-latency applications(such as audio/video streaming, highly interactive systems, etc) to meet their requirements in clouds. NFV is a new network concept which uses virtualization and software instead of dedicated network appliances. For some use cases of telecommunications, network latency must be within a certain range of values. Real-Time KVM can help NFV meet this requirements.
In this presentation, Pei Zhang will talk about:
(1)Real-Time KVM introduction
(2)Real-Time cloud building
(3)Real-Time KVM in NFV: VM with openvswitch, dpdk and qemu’s vhostuser
(4)Performance testing results show Zephyr: Creating a Best-of-Breed, Secure RTOS for IoT
Presentation delivered at LinuxCon China 2017.
Zephyr is an upstream open source project for places where Linux is too big to fit. This talk will overview the progress we've made in the first year towards the projects goals around incorporating best of breed technologies into the code base, and building up the community to support multiple architectures and development environments. We will share our roadmap, plans and the challenges ahead of the us and give an overview of the major technical challenges we want to tackle in 2017.
Policy-based Resource Placement
Resource placement is a policy-rich problem, particularly across multi-cluster, multi-geography and multi-cloud environments. Placement may be based on company conventions, external regulation, pricing, performance requirements, or complex combinations of those. Furthermore, placement policies evolve over time and vary across organizations. As a result, it is very difficult to anticipate the policy requirements of all users.
In this presentation, Torin Sandal (Lead Engineer of Open Policy Agent) will present, along with Irfan Ur Rehman, and demonstrate the work they've done integrating OPA into the Kubernetes Cluster Federation Control Plane. This enables high level policies to be expressed in a easy to understand policy language, and automatically enforced across federations of Kubernetes clusters.
OpenDaylight OpenStack Integration
Networking-odl and ODL Neutron Northbound are the key components for integrating OpenStack Neutron and OpenDaylight. They are actively developed open source projects. The document encourages giving the integration a try, providing feedback, and contributing to help further the integration of OpenStack and OpenDaylight networking.
Hyperledger Technical Community in China.
The Hyperledger Technical Community in China was founded in December 2016 and has over 10 volunteers. Its goals are to help build the China technical community, promote Hyperledger technical development, and focus on technical development, documentation and education, adoption and collaboration, and event organization. The community believes in open-source technologies and values trust, collaboration, mutual benefit, and openness.
Obstacles & Solutions for Livepatch Support on ARM64 Architecture
Obstacles & Solutions for Livepatch Support on ARM64 ArchitectureLinuxCon ContainerCon CloudOpen China
This document discusses obstacles and solutions for supporting live kernel patching (livepatching) on ARM64 architecture. Livepatching allows patching a running kernel without reboots. It is currently only supported on x86, s390 and powerpc. For ARM64, the main obstacle is that the ARM64 calling convention stores return addresses in a link register rather than the stack. The document proposes a solution that extends the profile instrumentation to save and restore the link register, allowing ftrace to be adapted for ARM64 livepatching. It provides an overview of upstream work on gcc and kernel support to enable livepatching for ARM64.Building a Better Thermostat
This document outlines Matthew Treinish's project to build a better thermostat using open source tools. It describes how he used a Z-Wave power switch and wireless temperature sensor to control the air conditioner and measure temperature. He implemented this using the Home Assistant home automation platform, setting up a generic thermostat device. Issues with reliability and manual configuration led to improvements such as automating temperature set points based on location tracking and scheduled times. Future work includes adding more sensors and automation functionality.
Viewers also liked (19)
From Resilient to Antifragile Chaos Engineering Primer
From Resilient to Antifragile Chaos Engineering Primer
Rebuild - Simplifying Embedded and IoT Development Using Linux Containers
Rebuild - Simplifying Embedded and IoT Development Using Linux Containers
GPU Acceleration for Containers on Intel Processor Graphics
GPU Acceleration for Containers on Intel Processor Graphics
High Performance Linux Virtual Machine on Microsoft Azure: SR-IOV Networking ...
High Performance Linux Virtual Machine on Microsoft Azure: SR-IOV Networking ...
点融网区块链即服务实践 - The Practice of Blockchain as a Service in Dianrong
点融网区块链即服务实践 - The Practice of Blockchain as a Service in Dianrong
See what happened with real time kvm when building real time cloud pezhang@re...
See what happened with real time kvm when building real time cloud pezhang@re...
Zephyr: Creating a Best-of-Breed, Secure RTOS for IoT
Zephyr: Creating a Best-of-Breed, Secure RTOS for IoT
Obstacles & Solutions for Livepatch Support on ARM64 Architecture
Obstacles & Solutions for Livepatch Support on ARM64 Architecture
Similar to Make Accelerator Pluggable for Container Engine
State of Containers and the Convergence of HPC and BigData
In this deck from 2018 Swiss HPC Conference, Christian Kniep from Docker Inc. presents: State of Containers and the Convergence of HPC and BigData.
"This talk will recap the history of and what constitutes Linux Containers, before laying out how the technology is employed by various engines and what problems these engines have to solve. Afterward Christian will elaborate on why the advent of standards for images and runtimes moved the discussion from building and distributing containers to orchestrating containerized applications at scale. In conclusion attendees will get an update on how containers foster the convergence of Big Data and HPC workloads and the state of native HPC containers."
Learn more: http://docker.com
and
http://www.hpcadvisorycouncil.com/events/2018/swiss-workshop/agenda.php
Sign up for our insideHPC Newsletter: http://insidehpc.com/newsletter
Instant scaling and deployment of Vitis Libraries on Alveo clusters using InA...
Instant scaling and deployment of Vitis Libraries on Alveo clusters using InA...Christoforos Kachris
This document discusses InAccel's FPGA orchestration platform. It provides instant and scalable deployment of FPGA applications through a unified API. The platform allows easy sharing of FPGA resources across multiple users and applications. It demonstrates scaling ResNet50 and Keras models on multiple Alveo cards with no code changes. The platform is integrated with Kubernetes and compatible with Xilinx tools like Vitis.CA Performance Manager Agility by using Docker Containers for Network Manag...
Everything is moving more quickly as companies try to achieve first-mover advantage by leveraging their network and offering advanced services. Join the experts at CA technologies to learn how using Docker containers can help expedite your testing and delivery of new network and product offerings.
For more information, please visit http://cainc.to/Nv2VOe
DCSF 19 Accelerating Docker Containers with NVIDIA GPUs
Using the NVIDIA Container Runtime, many developers and enterprises have been developing, benchmarking and deploying deep learning (DL) frameworks, HPC and other GPU accelerated containers at scale for the last two years. In this talk, we will go over the architecture of the NVIDIA Container Runtime and discuss our recent close collaboration with Docker. The result of our collaboration with Docker is a seamless native integration of the runtime enabling Docker Engine 19.03 CE and the forthcoming Docker Enterprise release to run GPU accelerated containers. We will also highlight containerized NVIDIA drivers. This new feature eliminates the overhead of provisioning GPU machines and brings GPU support on container optimized operating systems, which either lack package managers for installing software or require all applications to run in containers. In this session, you will learn how GPU accelerated containers can be easily built and deployed through the use of driver containers and native support for GPUs in Docker 19.03. The session will include a demo of running a GPU accelerated deep learning container using the new CLI options in Docker 19.03 and containerized drivers. Running NVIDIA GPU accelerated containers with Docker has never been this easy!
Delivering Docker & K3s worloads to IoT Edge devices
About 94% of AI Adopters are planning to use containers in the next 1 year. What’s driving this exponential growth? Faster time to deployment and Faster AI workload processing are the two major reasons. You can use GPUs in big data applications such as machine learning, data analytics, and genome sequencing. Docker containerization makes it easier for you to package and distribute applications. You can enable GPU support when using YARN on Docker containers. In this talk, I will demonstrate how Docker accelerates the AI workload development and deployment over the IoT Edge devices in efficient manner
Why you’re going to fail running java on docker!
This document discusses running Java applications on Docker containers and some of the challenges that can cause Java applications to fail when run this way. It begins by listing some big wins of using Docker for developers, such as portability and consistency across environments. It then discusses some potential cons, such as Docker not being a true virtual machine and portability issues. The document provides an overview of containers versus virtualization and the history of containers. It identifies specific challenges for Java applications related to seeing all host system resources rather than being constrained to container limits. Workarounds for memory and CPU limitations in Java are presented. The document emphasizes the importance of configuration for Java applications in containers.
No more Dockerfiles? Buildpacks to help you ship your image!
Do you always create a new Dockerfile for each new project?
Do you implement your own SSL certificate logic in this Dockerfile?
Do you forget to update your base image version?
Do you wonder how to generate a Bill Of Material to comply with your organization requirements?
Have you answered yes to any of those questions? Come and attend this talk to learn a new way to build your images, all use cases included - demos provided along the way!
Ceph Day Shanghai - Hyper Converged PLCloud with Ceph
Hyper Converged PLCloud with CEPH
This document discusses PowerLeader Cloud (PLCloud), a cloud computing platform that uses a hyper-converged infrastructure with OpenStack, Docker, and Ceph. It provides an overview of PLCloud and how it has adopted OpenStack, Ceph, and other open source technologies. It then describes PLCloud's hyper-converged architecture and how it leverages OpenStack, Docker, and Ceph. Finally, it discusses a specific use case where Ceph RADOS Gateway is used for media storage and access in PLCloud.
Dayta AI Seminar - Kubernetes, Docker and AI on Cloud
Kubernetes is an open-source system for automating deployment, scaling, and management of containerized applications. It groups containers that make up an application into logical units for easy management and discovery. Kubernetes services expose these units to enable dynamic load balancing while maintaining session affinity. It also provides self-healing capabilities by restarting containers that fail, replacing them, and killing containers that don't respond to their health check.
Develop QNAP NAS App by Docker
This document provides information on developing QNAP NAS apps using Docker. It introduces Docker and how apps can be packaged and run as Docker containers on QNAP NAS. It discusses using QDK/QDK2 to build QPKG packages for apps and deploying them to QNAP NAS through Container Station. Examples of building a Ghost blogging platform app and debugging techniques are also presented. The document aims to educate developers on leveraging Docker for app development on QNAP NAS.
DevFest 2022 - Cloud Workstation Introduction TaiChung
Cloud Workstations provides preconfigured, customizable, and secure managed development environments on Google Cloud. Cloud Workstations is accessible through a browser-based IDE, from multiple local code editors (such as IntelliJ IDEA Ultimate or VS Code), or through SSH. Instead of manually setting up development environments, you can create a workstation configuration specifying your environment in a reproducible way
Simplifying and accelerating converged media with Open Visual Cloud
Challenges exist with media transformation into Visual Cloud services and the flexibility to migrate those services to new HW platforms. Learn how Intel and partners are solving these challenges with highly optimized cloud native media processing, media analytics, and graphics/rendering components to quickly and easily deliver end-to-end visual cloud services with scalable open source software. Two visual cloud services around media delivery and media analytics will be demonstrated to showcase how to enable faster time to market for innovative “new media” services.
Node.js, Vagrant, Chef, and Mathoid @ Benetech
Vagrant allows developers to quickly set up uniform development environments for Node.js projects. It uses configuration files to define and provision virtual machines with all necessary tools and libraries. Chef is used for configuration management, ensuring environments are identical. Vagrant provides portability and abstraction, allowing environments to run on different providers like VirtualBox or cloud services.
Introduction to Docker
Remix of two other open source presentations along with my own content, 40 slides set to play at 20 seconds auto-timed (similar to Pecha-Kucha style timing). This was delivered via Caribbean Tech Dev forum's monthly Google Hangout in November 2015, and video can be viewed at https://www.youtube.com/watch?v=xANrsSin_-0
Docker engine - Indroduc
Docker is a tool that allows developers to package applications and dependencies into containers that can be run anywhere. The document discusses how Docker eliminates complexity by allowing developers to build, ship and run distributed applications using containers. It provides instructions on how to install Docker and create a simple "hello world" Docker container to demonstrate its basic functionality.
Automate drupal deployments with linux containers, docker and vagrant
This document discusses strategies for automating Drupal deployments using Linux containers, Vagrant, and Docker. It begins with an overview of virtual machines and their disadvantages compared to containers. It then covers using Linux containers (LXC), Vagrant, and Docker to build and deploy containerized Drupal environments that can be easily reproduced and deployed across different systems. The document provides examples of building Drupal containers using LXC, Vagrant, and Docker that take advantage of their portability and reproducibility.
Building a data warehouse with Pentaho and Docker
EDW CENIPA is a opensource project designed to enable analysis of aeronautical incidentes that occured in the brazilian civil aviation. The project uses techniques and BI tools that explore innovative low-cost technologies. Historically, Business Intelligence platforms are expensive and impracticable for small projects. BI projects require specialized skills and high development costs. This work aims to break this barrier.
Containerizing GPU Applications with Docker for Scaling to the Cloud
This document discusses containerizing GPU applications with Docker to enable scaling to the cloud. It describes how containers can solve problems of hardware and software portability by allowing applications to run consistently across different infrastructure. The document demonstrates how to build a GPU container using Dockerfiles and deploy it across multiple clouds. It also introduces Boost Containers which combine Bitfusion Boost technology with containers to build virtual GPU machines and clusters, enabling flexible scheduling of GPU workflows without code changes.
Scaleable PHP Applications in Kubernetes
Kubernetes is also called the "distributed Linux of the cloud" – which implies that it provides fundamental infrastructure, which can solve a lot of challenges. Let’s see how PHP applications fit into this picture. In this presentation, we are going to explore when Kubernetes is a good fit for operating your PHP application and how it can be done in practice. We’ll look at the whole lifecycle: how to build your application, create or choose the right Docker images, deploy and scale, and how to deal with performance and monitoring. At the end you will have a good understanding about all the different stages and building blocks for running a PHP application with Kubernetes in production.
Hands on Docker - Launch your own LEMP or LAMP stack - SunshinePHP
In this tutorial we will go over setting up a standard LEMP stack for development use and learn how to modify it to mimic your production/pre-production environments as closely as possible. We will go over how to switch from Nginx to Apache, upgrade PHP versions and introduce additional storage engines such as Redis to the equation. We'll also step through how to run both unit and acceptance suites using headless Selenium images in the stack. Leave here fully confident in knowing that whatever environment you get thrown into, you can replicate it and work in it comfortably.
Similar to Make Accelerator Pluggable for Container Engine (20)
State of Containers and the Convergence of HPC and BigData
State of Containers and the Convergence of HPC and BigData
Instant scaling and deployment of Vitis Libraries on Alveo clusters using InA...
Instant scaling and deployment of Vitis Libraries on Alveo clusters using InA...
CA Performance Manager Agility by using Docker Containers for Network Manag...
CA Performance Manager Agility by using Docker Containers for Network Manag...
DCSF 19 Accelerating Docker Containers with NVIDIA GPUs
DCSF 19 Accelerating Docker Containers with NVIDIA GPUs
Delivering Docker & K3s worloads to IoT Edge devices
Delivering Docker & K3s worloads to IoT Edge devices
No more Dockerfiles? Buildpacks to help you ship your image!
No more Dockerfiles? Buildpacks to help you ship your image!
Ceph Day Shanghai - Hyper Converged PLCloud with Ceph
Ceph Day Shanghai - Hyper Converged PLCloud with Ceph
Dayta AI Seminar - Kubernetes, Docker and AI on Cloud
Dayta AI Seminar - Kubernetes, Docker and AI on Cloud
DevFest 2022 - Cloud Workstation Introduction TaiChung
DevFest 2022 - Cloud Workstation Introduction TaiChung
Simplifying and accelerating converged media with Open Visual Cloud
Simplifying and accelerating converged media with Open Visual Cloud
Automate drupal deployments with linux containers, docker and vagrant
Automate drupal deployments with linux containers, docker and vagrant
Containerizing GPU Applications with Docker for Scaling to the Cloud
Containerizing GPU Applications with Docker for Scaling to the Cloud
Hands on Docker - Launch your own LEMP or LAMP stack - SunshinePHP
Hands on Docker - Launch your own LEMP or LAMP stack - SunshinePHP
More from LinuxCon ContainerCon CloudOpen China
SecurityPI - Hardening your IoT endpoints in Home.
A lot of Internet of things devices use linux as its core. More so with the advent of DIY projects and Internet of things projects. A lot of Raspberry PI's, Beaglebone, Tessel boards are out there with default settings, and all connected to the internet, ready to be taken over. With the recent dyn DNS attack its of prime importance to know how we can keep these end point devices secure and out of the hands of botnet hoarders, attackers. In this presentation Rabimba Karanjai will show how to harden the security on these endpint devices taking a RaspBerry PI as an example. He will explain different techniques with code examples along with a toolkit made specifically for this demo which will make devices considerable harder to compromise. And even when they are, will allow to locate and detect the breach. After all, proetcting the device fially protects us all (prevents another DDOS)
Flowchain: A case study on building a Blockchain for the IoT
The Blockchain for the Internet of Things (IoT) has considered to "change the future." Despite a myriad of studies on the blockchain IoT, few studies have investigated how an IoT blockchain system develops with open source technologies, open standards, web technologies, and a p2p network. In this presentation, Jollen will share the Flowchain case study, an open source IoT blockchain project in Node.js; he will discuss the practice, the technical challenges, and the engineering experiences. Furthermore, to provide the real-time data transaction capabilities for current IoT requirements, he will utilize the "virtual block" idea to facilitate such technical challenges.
Introduction to OCI Image Technologies Serving Container
The document introduces OCI image technologies, including the OCI image specification and image tools. It describes the key components of an OCI image like the image manifest, layers, and configuration. It also outlines the features and workflow of image tools, such as creating, unpacking, and validating OCI images. Finally, it discusses concepts like distribution, signatures, and the relationship between image tools and OCI consumers.
UEFI HTTP/HTTPS Boot
Presentation delivered at LinuxCon China 2016
UEFI HTTP/HTTPS Boot is a new feature of UEFI 2.5+. In the meantime, this feature is not yet implemented in any Linux bootloader. This Birds of a Feather session will give an introduction to UEFI HTTP/HTTPS Boot, and share a proof-of-concept implementation based on grub2 that works on both the emulator (QEMU/OVMF) and HPE ProLiant Gen10 servers.
For HTTPS, the experience and comparison will be shared between the purely software-based and UEFI-based implementations in the aspects of ease of implementation, security strength, and limitation.
How Open Source Communities do Standardization
This document discusses how open source communities can effectively do standardization. It addresses some challenges open source communities face in standardization, including unclear customer requirements, fast innovation cycles misaligned with industry cadence, and differences between coding and standardization processes. It provides principles for open source standardization, such as being customer-centric and identifying requirements early, and leveraging existing standards where possible rather than duplicating efforts. The overall goal of standardization for open source is to help unlock the business value of open source technologies for customers.
Fully automated kubernetes deployment and management
Fully Automated Kubernetes Deployment and Management (Peng Jiang, Rancher Labs) - Kubernetes is rapidly gaining popularity as a powerful container orchestration and scheduling platform. But deploying and managing Kubernetes clusters is still a challenge for many organizations.How to ensure Kubernetes clusters in different clouds and data centers can communicate with each other? How to automate the deployment of multiple Kubernetes clusters? How to incorporate the new Kubernetes Federation into multi cloud and multi datacenter deployments? How to manage the health of Kubernetes cluster itself? etc.
In this talk, Peng will share his experience on how to automate and simplify Kubernetes deployments, and discuss how some of the latest community projects (such as kubeadm and self-hosting Kubernetes) will help address the problems in the future.
Is there still room for innovation in container orchestration and scheduling
Is there still room for innovation in container orchestration and scheduling LinuxCon ContainerCon CloudOpen China
In the container ecosystem, there is perhaps no technology that has received more focus and attention than orchestration and scheduling. Mesos, Kubernetes, and Swarm have established themselves as the leading technology choices in this space.
In this talk, Sheng will discuss what he learned from working directly with hundreds of users who have deployed one of these frameworks. He will look at how these frameworks will continue to evolve and if there’re any gaps and opportunities in container orchestration and scheduling. Sheng will make a case that there are still room for innovation and new orchestration and scheduling frameworks will be created in the future. He will discuss what new frameworks might look like--the features, functionalities, and attributes that differentiate them from the mainstream frameworks today. More from LinuxCon ContainerCon CloudOpen China (8)
SecurityPI - Hardening your IoT endpoints in Home.
SecurityPI - Hardening your IoT endpoints in Home.
Flowchain: A case study on building a Blockchain for the IoT
Flowchain: A case study on building a Blockchain for the IoT
Introduction to OCI Image Technologies Serving Container
Introduction to OCI Image Technologies Serving Container
Fully automated kubernetes deployment and management
Fully automated kubernetes deployment and management
Is there still room for innovation in container orchestration and scheduling
Is there still room for innovation in container orchestration and scheduling
Recently uploaded
20240609 QFM020 Irresponsible AI Reading List May 2024
Everything I found interesting about the irresponsible use of machine intelligence in May 2024
National Security Agency - NSA mobile device best practices
Threats to mobile devices are more prevalent and increasing in scope and complexity. Users of mobile devices desire to take full advantage of the features
available on those devices, but many of the features provide convenience and capability but sacrifice security. This best practices guide outlines steps the users can take to better protect personal devices and information.
“Building and Scaling AI Applications with the Nx AI Manager,” a Presentation...
“Building and Scaling AI Applications with the Nx AI Manager,” a Presentation...Edge AI and Vision Alliance
For the full video of this presentation, please visit: https://www.edge-ai-vision.com/2024/06/building-and-scaling-ai-applications-with-the-nx-ai-manager-a-presentation-from-network-optix/
Robin van Emden, Senior Director of Data Science at Network Optix, presents the “Building and Scaling AI Applications with the Nx AI Manager,” tutorial at the May 2024 Embedded Vision Summit.
In this presentation, van Emden covers the basics of scaling edge AI solutions using the Nx tool kit. He emphasizes the process of developing AI models and deploying them globally. He also showcases the conversion of AI models and the creation of effective edge AI pipelines, with a focus on pre-processing, model conversion, selecting the appropriate inference engine for the target hardware and post-processing.
van Emden shows how Nx can simplify the developer’s life and facilitate a rapid transition from concept to production-ready applications.He provides valuable insights into developing scalable and efficient edge AI solutions, with a strong focus on practical implementation.Infrastructure Challenges in Scaling RAG with Custom AI models
Building Retrieval-Augmented Generation (RAG) systems with open-source and custom AI models is a complex task. This talk explores the challenges in productionizing RAG systems, including retrieval performance, response synthesis, and evaluation. We’ll discuss how to leverage open-source models like text embeddings, language models, and custom fine-tuned models to enhance RAG performance. Additionally, we’ll cover how BentoML can help orchestrate and scale these AI components efficiently, ensuring seamless deployment and management of RAG systems in the cloud.
Ocean lotus Threat actors project by John Sitima 2024 (1).pptx
Ocean Lotus cyber threat actors represent a sophisticated, persistent, and politically motivated group that poses a significant risk to organizations and individuals in the Southeast Asian region. Their continuous evolution and adaptability underscore the need for robust cybersecurity measures and international cooperation to identify and mitigate the threats posed by such advanced persistent threat groups.
Essentials of Automations: The Art of Triggers and Actions in FME
In this second installment of our Essentials of Automations webinar series, we’ll explore the landscape of triggers and actions, guiding you through the nuances of authoring and adapting workspaces for seamless automations. Gain an understanding of the full spectrum of triggers and actions available in FME, empowering you to enhance your workspaces for efficient automation.
We’ll kick things off by showcasing the most commonly used event-based triggers, introducing you to various automation workflows like manual triggers, schedules, directory watchers, and more. Plus, see how these elements play out in real scenarios.
Whether you’re tweaking your current setup or building from the ground up, this session will arm you with the tools and insights needed to transform your FME usage into a powerhouse of productivity. Join us to discover effective strategies that simplify complex processes, enhancing your productivity and transforming your data management practices with FME. Let’s turn complexity into clarity and make your workspaces work wonders!
Things to Consider When Choosing a Website Developer for your Website | FODUU
Choosing the right website developer is crucial for your business. This article covers essential factors to consider, including experience, portfolio, technical skills, communication, pricing, reputation & reviews, cost and budget considerations and post-launch support. Make an informed decision to ensure your website meets your business goals.
Artificial Intelligence for XMLDevelopment
In the rapidly evolving landscape of technologies, XML continues to play a vital role in structuring, storing, and transporting data across diverse systems. The recent advancements in artificial intelligence (AI) present new methodologies for enhancing XML development workflows, introducing efficiency, automation, and intelligent capabilities. This presentation will outline the scope and perspective of utilizing AI in XML development. The potential benefits and the possible pitfalls will be highlighted, providing a balanced view of the subject.
We will explore the capabilities of AI in understanding XML markup languages and autonomously creating structured XML content. Additionally, we will examine the capacity of AI to enrich plain text with appropriate XML markup. Practical examples and methodological guidelines will be provided to elucidate how AI can be effectively prompted to interpret and generate accurate XML markup.
Further emphasis will be placed on the role of AI in developing XSLT, or schemas such as XSD and Schematron. We will address the techniques and strategies adopted to create prompts for generating code, explaining code, or refactoring the code, and the results achieved.
The discussion will extend to how AI can be used to transform XML content. In particular, the focus will be on the use of AI XPath extension functions in XSLT, Schematron, Schematron Quick Fixes, or for XML content refactoring.
The presentation aims to deliver a comprehensive overview of AI usage in XML development, providing attendees with the necessary knowledge to make informed decisions. Whether you’re at the early stages of adopting AI or considering integrating it in advanced XML development, this presentation will cover all levels of expertise.
By highlighting the potential advantages and challenges of integrating AI with XML development tools and languages, the presentation seeks to inspire thoughtful conversation around the future of XML development. We’ll not only delve into the technical aspects of AI-powered XML development but also discuss practical implications and possible future directions.
HCL Notes and Domino License Cost Reduction in the World of DLAU
Webinar Recording: https://www.panagenda.com/webinars/hcl-notes-and-domino-license-cost-reduction-in-the-world-of-dlau/
The introduction of DLAU and the CCB & CCX licensing model caused quite a stir in the HCL community. As a Notes and Domino customer, you may have faced challenges with unexpected user counts and license costs. You probably have questions on how this new licensing approach works and how to benefit from it. Most importantly, you likely have budget constraints and want to save money where possible. Don’t worry, we can help with all of this!
We’ll show you how to fix common misconfigurations that cause higher-than-expected user counts, and how to identify accounts which you can deactivate to save money. There are also frequent patterns that can cause unnecessary cost, like using a person document instead of a mail-in for shared mailboxes. We’ll provide examples and solutions for those as well. And naturally we’ll explain the new licensing model.
Join HCL Ambassador Marc Thomas in this webinar with a special guest appearance from Franz Walder. It will give you the tools and know-how to stay on top of what is going on with Domino licensing. You will be able lower your cost through an optimized configuration and keep it low going forward.
These topics will be covered
- Reducing license cost by finding and fixing misconfigurations and superfluous accounts
- How do CCB and CCX licenses really work?
- Understanding the DLAU tool and how to best utilize it
- Tips for common problem areas, like team mailboxes, functional/test users, etc
- Practical examples and best practices to implement right away
みなさんこんにちはこれ何文字まで入るの？40文字以下不可とか本当に意味わからないけどこれ限界文字数書いてないからマジでやばい文字数いけるんじゃないの？えこ...
ここ3000字までしか入らないけどタイトルの方がたくさん文字入ると思います。
20240607 QFM018 Elixir Reading List May 2024
Everything I found interesting about the Elixir programming ecosystem in May 2024
AI-Powered Food Delivery Transforming App Development in Saudi Arabia.pdf
In this blog post, we'll delve into the intersection of AI and app development in Saudi Arabia, focusing on the food delivery sector. We'll explore how AI is revolutionizing the way Saudi consumers order food, how restaurants manage their operations, and how delivery partners navigate the bustling streets of cities like Riyadh, Jeddah, and Dammam. Through real-world case studies, we'll showcase how leading Saudi food delivery apps are leveraging AI to redefine convenience, personalization, and efficiency.
Removing Uninteresting Bytes in Software Fuzzing
Imagine a world where software fuzzing, the process of mutating bytes in test seeds to uncover hidden and erroneous program behaviors, becomes faster and more effective. A lot depends on the initial seeds, which can significantly dictate the trajectory of a fuzzing campaign, particularly in terms of how long it takes to uncover interesting behaviour in your code. We introduce DIAR, a technique designed to speedup fuzzing campaigns by pinpointing and eliminating those uninteresting bytes in the seeds. Picture this: instead of wasting valuable resources on meaningless mutations in large, bloated seeds, DIAR removes the unnecessary bytes, streamlining the entire process.
In this work, we equipped AFL, a popular fuzzer, with DIAR and examined two critical Linux libraries -- Libxml's xmllint, a tool for parsing xml documents, and Binutil's readelf, an essential debugging and security analysis command-line tool used to display detailed information about ELF (Executable and Linkable Format). Our preliminary results show that AFL+DIAR does not only discover new paths more quickly but also achieves higher coverage overall. This work thus showcases how starting with lean and optimized seeds can lead to faster, more comprehensive fuzzing campaigns -- and DIAR helps you find such seeds.
- These are slides of the talk given at IEEE International Conference on Software Testing Verification and Validation Workshop, ICSTW 2022.
June Patch Tuesday
Ivanti’s Patch Tuesday breakdown goes beyond patching your applications and brings you the intelligence and guidance needed to prioritize where to focus your attention first. Catch early analysis on our Ivanti blog, then join industry expert Chris Goettl for the Patch Tuesday Webinar Event. There we’ll do a deep dive into each of the bulletins and give guidance on the risks associated with the newly-identified vulnerabilities.
HCL Notes und Domino Lizenzkostenreduzierung in der Welt von DLAU
Webinar Recording: https://www.panagenda.com/webinars/hcl-notes-und-domino-lizenzkostenreduzierung-in-der-welt-von-dlau/
DLAU und die Lizenzen nach dem CCB- und CCX-Modell sind für viele in der HCL-Community seit letztem Jahr ein heißes Thema. Als Notes- oder Domino-Kunde haben Sie vielleicht mit unerwartet hohen Benutzerzahlen und Lizenzgebühren zu kämpfen. Sie fragen sich vielleicht, wie diese neue Art der Lizenzierung funktioniert und welchen Nutzen sie Ihnen bringt. Vor allem wollen Sie sicherlich Ihr Budget einhalten und Kosten sparen, wo immer möglich. Das verstehen wir und wir möchten Ihnen dabei helfen!
Wir erklären Ihnen, wie Sie häufige Konfigurationsprobleme lösen können, die dazu führen können, dass mehr Benutzer gezählt werden als nötig, und wie Sie überflüssige oder ungenutzte Konten identifizieren und entfernen können, um Geld zu sparen. Es gibt auch einige Ansätze, die zu unnötigen Ausgaben führen können, z. B. wenn ein Personendokument anstelle eines Mail-Ins für geteilte Mailboxen verwendet wird. Wir zeigen Ihnen solche Fälle und deren Lösungen. Und natürlich erklären wir Ihnen das neue Lizenzmodell.
Nehmen Sie an diesem Webinar teil, bei dem HCL-Ambassador Marc Thomas und Gastredner Franz Walder Ihnen diese neue Welt näherbringen. Es vermittelt Ihnen die Tools und das Know-how, um den Überblick zu bewahren. Sie werden in der Lage sein, Ihre Kosten durch eine optimierte Domino-Konfiguration zu reduzieren und auch in Zukunft gering zu halten.
Diese Themen werden behandelt
- Reduzierung der Lizenzkosten durch Auffinden und Beheben von Fehlkonfigurationen und überflüssigen Konten
- Wie funktionieren CCB- und CCX-Lizenzen wirklich?
- Verstehen des DLAU-Tools und wie man es am besten nutzt
- Tipps für häufige Problembereiche, wie z. B. Team-Postfächer, Funktions-/Testbenutzer usw.
- Praxisbeispiele und Best Practices zum sofortigen Umsetzen
Best 20 SEO Techniques To Improve Website Visibility In SERP
Boost your website's visibility with proven SEO techniques! Our latest blog dives into essential strategies to enhance your online presence, increase traffic, and rank higher on search engines. From keyword optimization to quality content creation, learn how to make your site stand out in the crowded digital landscape. Discover actionable tips and expert insights to elevate your SEO game.
TrustArc Webinar - 2024 Global Privacy Survey
How does your privacy program stack up against your peers? What challenges are privacy teams tackling and prioritizing in 2024?
In the fifth annual Global Privacy Benchmarks Survey, we asked over 1,800 global privacy professionals and business executives to share their perspectives on the current state of privacy inside and outside of their organizations. This year’s report focused on emerging areas of importance for privacy and compliance professionals, including considerations and implications of Artificial Intelligence (AI) technologies, building brand trust, and different approaches for achieving higher privacy competence scores.
See how organizational priorities and strategic approaches to data security and privacy are evolving around the globe.
This webinar will review:
- The top 10 privacy insights from the fifth annual Global Privacy Benchmarks Survey
- The top challenges for privacy leaders, practitioners, and organizations in 2024
- Key themes to consider in developing and maintaining your privacy program
20240605 QFM017 Machine Intelligence Reading List May 2024
Everything I found interesting about machines behaving intelligently during May 2024
Recently uploaded (20)
20240609 QFM020 Irresponsible AI Reading List May 2024
20240609 QFM020 Irresponsible AI Reading List May 2024
National Security Agency - NSA mobile device best practices
National Security Agency - NSA mobile device best practices
“Building and Scaling AI Applications with the Nx AI Manager,” a Presentation...
“Building and Scaling AI Applications with the Nx AI Manager,” a Presentation...
Infrastructure Challenges in Scaling RAG with Custom AI models
Infrastructure Challenges in Scaling RAG with Custom AI models
Ocean lotus Threat actors project by John Sitima 2024 (1).pptx
Ocean lotus Threat actors project by John Sitima 2024 (1).pptx
Essentials of Automations: The Art of Triggers and Actions in FME
Essentials of Automations: The Art of Triggers and Actions in FME
Things to Consider When Choosing a Website Developer for your Website | FODUU
Things to Consider When Choosing a Website Developer for your Website | FODUU
HCL Notes and Domino License Cost Reduction in the World of DLAU
HCL Notes and Domino License Cost Reduction in the World of DLAU
みなさんこんにちはこれ何文字まで入るの？40文字以下不可とか本当に意味わからないけどこれ限界文字数書いてないからマジでやばい文字数いけるんじゃないの？えこ...
みなさんこんにちはこれ何文字まで入るの？40文字以下不可とか本当に意味わからないけどこれ限界文字数書いてないからマジでやばい文字数いけるんじゃないの？えこ...
AI-Powered Food Delivery Transforming App Development in Saudi Arabia.pdf
AI-Powered Food Delivery Transforming App Development in Saudi Arabia.pdf
HCL Notes und Domino Lizenzkostenreduzierung in der Welt von DLAU
HCL Notes und Domino Lizenzkostenreduzierung in der Welt von DLAU
Best 20 SEO Techniques To Improve Website Visibility In SERP
Best 20 SEO Techniques To Improve Website Visibility In SERP
20240605 QFM017 Machine Intelligence Reading List May 2024
20240605 QFM017 Machine Intelligence Reading List May 2024
Make Accelerator Pluggable for Container Engine
- 1. www.huawei.com HUAWEI TECHNOLOGIES CO., LTD. Make Accelerator Pluggable for Container Engine Author/ Email: Jiuyue Ma / majiuyue@huawei.com Version: V1.0 (20150504)
- 2. HUAWEI TECHNOLOGIES CO., LTD. 2 Today’s Topic Container Engine Hardware Accelerators e.g. GPU、QAT、FPGA OLTP/OLAP BigData Processing Neural Network CloudRAN Pluggable Accelerator Support for Container Engine
- 3. HUAWEI TECHNOLOGIES CO., LTD. 3 Agenda Use accelerator in containers and How? Key problems to deal with Identify accelerator requirements Prepare accelerator runtimes Manage accelerator resources Further development
- 4. HUAWEI TECHNOLOGIES CO., LTD. 4 Why Container?
- 5. HUAWEI TECHNOLOGIES CO., LTD. 5 Why Container? Why NOT Container? * Raphael Da Silva. OPEN SOURCE TECHNOLOGY: Docker Containers on IBM Bluemix. 2015.
- 6. HUAWEI TECHNOLOGIES CO., LTD. 6 CPU is not fast/effective/… enough Heterogeneous is the future Nvidia GPU-compute, Intel Skylake Xeon+FPGA, AWS P2/F1 Instance use the right processor, in the right place, at the right time Why Accelerator? Container a.k.a. Docker [baidu, HotChips 2016]
- 7. HUAWEI TECHNOLOGIES CO., LTD. 7 Google it ! “Use XXX in docker” NVIDIA’s GPU-Docker Solution DPDK FPGA GPU
- 8. HUAWEI TECHNOLOGIES CO., LTD. 8 Use GPU in Docker (from nvidia-docker) Wrapped Command docker run --volume-driver=nvidia-docker --volume=nvidia_driver_361.48:/usr/local/nvidia:ro ③ nvidia-docker cli-wrapper $ ldconfig -p | grep -E 'nvidia|cuda' libnvidia-ml.so (libc6,x86-64) => /usr/lib/nvidia-361/libnvidia-ml.so libnvidia-glcore.so.361.48 (libc6,x86-64) => /usr/lib/nvidia-361/lib… libnvidia-compiler.so.361.48 (libc6,x86-64) => /usr/lib/nvidia-361/lib… libcuda.so (libc6,x86-64) => /usr/lib/x86_64-linux-gnu/libcuda.so ... $ lsmod | grep nvidia nvidia_uvm 711531 2 nvidia_modeset 742329 0 nvidia 10058469 80 nvidia_modeset,nvidia_uvm Key Problem：VERSION MISMATCH $ nvidia-smi Failed to initialize NVML: Driver/library version mismatch ② VOLUME: nvidia-docker/nvidia_driver_361.48 ① Labeled Image LABEL com.nvidia.volumes.needed="nvidia_driver" LABEL com.nvidia.cuda.version="7.5" • detect/check cuda version • hook docker cli args --volume-driver / --volume nvidia
- 9. HUAWEI TECHNOLOGIES CO., LTD. 9 Do we really need “nvidia-docker”? If so, we also need: dpdk-docker, qat-docker, fpga-docker, … But, if we need both GPU and DPDK? nvidia DPDK QAT FPGA DPDK nvidia Pluggable Accelerator
- 10. HUAWEI TECHNOLOGIES CO., LTD. 10 Device Files (-d device) /dev/nvidia0 /dev/nvidia-smi /dev/nvidia-uvm /dev/uio0 /dev/fpga0 File Bindings (-v src:dest) /usr/lib/nvidia-361/libnvidia-ml.so /usr/lib/nvidia-361/libnvidia-glcore.so.361.48 /usr/lib/nvidia-361/libnvidia- compiler.so.361.48 /usr/lib/x86_64-linux-gnu/libcuda.so ... /sys/bus/pci/devices/xxxx:xx:xx.x /dev/hugepages /usr/lib/libfpga.so /sys/bus/pci/devices/xxxx:xx:xx.x /dev/hugepages Environments (-e env) PATH=$PATH:/usr/lib/nvidia-361/bin LD_LIBRARY_PATH=… Pluggable Accelerator, How? What’s the difference? nvidia DPDK FPGA Accelerator Plugin Interface in-house FPGA Accel
- 11. HUAWEI TECHNOLOGIES CO., LTD. 11 Implementation (1/3): IDENTIFY Accelerator Requirements We are using the function provided by device, not the device itself Identified by runtime instead of device e.g. “A SHA256 accelerator” instead of “A FPGA with XXXX-bitstream” Identify user requirements Integrate into image Specify when start container Identify device capabilities Identified by “accelerator plugin” Report to engine through plugin api LABEL runtime gpu0=cuda:7.5 $ docker run --accel fpga:crypto huawei/crypto-image image cli / rest-api dockerd Device Accel Runtime /dev/nvidia0 cuda:7.5, cuda:8.0, OpenCL 2.0, … /dev/qat0 md5, sha256, aes, … /dev/fpga0 crypto, compress, decode, … Accelerator Plugin Plugin API
- 12. HUAWEI TECHNOLOGIES CO., LTD. 12 Implementation (2/3): PREPARE Select plugin from accelerator requirements Device initialization by plugin Dynamic inject required libraries & devices DPDK-plugin - eal.so/… - igb_uio.ko - /dev/uioX FPGA-plugin - fpga.so - fpga.ko - /dev/fpgaX container Host Application fpga.ko v1 dockerd /dev/fpga0 generate bind libacc accel requirements PaaS fpga.so/dev/fpga0 fpga.so v1 (2) mount userspace lib (3) mount device GPU-plugin - gpu.so / cuda.so - gpu.ko - /dev/gpuX QAT-plugin - qat.so - qat.ko - /dev/qatX
- 13. HUAWEI TECHNOLOGIES CO., LTD. 13 Implementation (3/3): MANAGEMENT Running CreatedStopped CreatingDeleting INIT Container Life-Cycles allocate persistent allocate non-persistent release non-persistent release persistent prepare parse accel requirements Accelerator Plugin Accelerator Life-Cycle Allocate Prepare Release Plugin hooks for each stage Integrate with Container Life- Cycle Persistent：CreateDelete Non-persistent： StartStop
- 14. HUAWEI TECHNOLOGIES CO., LTD. 14 Example Flow
- 15. HUAWEI TECHNOLOGIES CO., LTD. 15 Further Developments Standardize “Accelerator Runtime” OCI Runtime/Image Spec should be good place Integrate with Docker Swarm / K8S / etc Cluster level accelerator schedule&management More Features Accelerator Sharing Accelerator Exception Interface Accelerator Hot-Plug …
- 16. Copyright© 2011 Huawei Technologies Co., Ltd. All Rights Reserved. The information in this document may contain predictive statements including, without limitation, statements regarding the future financial and operating results, future product portfolio, new technology, etc. There are a number of factors that could cause actual results and developments to differ materially from those expressed or implied in the predictive statements. Therefore, such information is provided for reference purpose only and constitutes neither an offer nor an acceptance. Huawei may change the information at any time without notice. Thank you www.huawei.com