Easy Deployment of Workload-Optimized OpenStack with JetPack
Learn how to easily deploy workload-optimized OpenStack using JetPack, a comprehensive solution that provides flexibility in hardware configurations and automated lifecycle management. JetPack, integrated with TripleO, offers predefined profiles for specific workloads, enabling customization beyond standard features.
Uploaded on | 0 Views
Download Presentation
Please find below an Image/Link to download the presentation.
The content on the website is provided AS IS for your information and personal use only. It may not be sold, licensed, or shared on other websites without obtaining consent from the author. If you encounter any issues during the download, it is possible that the publisher has removed the file from their server.
You are allowed to download the files provided on this website for personal or commercial use, subject to the condition that they are used lawfully. All files are the property of their respective owners.
The content on the website is provided AS IS for your information and personal use only. It may not be sold, licensed, or shared on other websites without obtaining consent from the author.
E N D
Presentation Transcript
Workload Optimized OpenStack made easy Arkady Kanevsky Arkady Kanevsky Service Provider Organization, Dell EMC Service Provider Organization, Dell EMC
Workload Optimized? 1. 1. Choice of HW components specific for Workload Choice of HW components specific for Workload 1. 1. NIC with PF support and offload for NFV workload NIC with PF support and offload for NFV workload 2. 2. Combination of NVMe and HDDs for Hadoop Combination of NVMe and HDDs for Hadoop 3. 3. GPU GPUs and FPGAs for Machine Learning or HPC s and FPGAs for Machine Learning or HPC 2. 2. HW configuration HW configuration 1. BIOS setting for virtualization acceleration 2. Processor off-load for encryption, Secure Boot 3. OpenStack configuration 1. Huge Page, NUMA pinning 4. Orchestrate and coordinate for all of them
How do you put it all together? JetPack and TripleO Open Source Project - https://github.com/dsp-jetpack/JetPack Deployment and Lifecycle Flexibility specific to a workload Predefined Profiles for specific Workloads: Telco/NFV, Generic Service Provider/xSP Flexibility to customize all features beyond predefined profiles Layered on top of TripleO and Ironic
How do you put it all together? JetPack and TripleO Technical: Technical: Deployment and Lifecycle Flexibility Feature set In-place Upgrades Part of OpenStack project / standards Business: Business: Partner Ecosystem Award winning, follow the sun support Entire Stack ownership Know-how
JetPack Overview The Context The Approach Red Hat OSP Day-0 Enablement embedded within standard deployment by JetPack Red Hat OSP Director Day-N Compute and Storage node addition or removal and Cloud updates by JetPack Dell EMC Jetstream JetPack automated life-cycle management software https://github.com/dsp-jetpack/JetPack Feature Set specific to Workload part of JetPack profile JetPack configures servers in optimized way for Workload defined by Profile
What is Profile? A profile is basically a fixed set of configuration options in the automation files For the deployment of a particular workload, there are certain features that need to be set in a pre-specified way; all other features/settings are set to defaults. Sample features: IP Addresses, vLAN IDs, NIC Configuration, MTU size, HugePage size/count vcpu pin set, Ceph OSD/Journal choices, OVS enabled to use DPDK SR-IOV for external-facing networks, choice of PFs (physical functions aka ports) for use with SR-IOV, NIC Alignment for external-facing SR-IOV networks, DVR IPv6 for tenant network only
Take aways In order to provide complete solution hardware and software need to be developed and integrated together Minimize deployment risk by selecting good partners with know-how Look for value-add features that enhance OpenStack experience
