The Must-Attend

Open Infrastructure Event

The open infrastructure landscape is changing, and so is the Summit. Now that users are integrating dozens of open source tools into a modern stack that reaches well beyond the scope of OpenStack, we’re re-organizing the event to focus on specific problem domains like container infrastructure, edge computing and CI/CD and we are focusing on the hard work of integrating all of these tools developed in disparate communities. This is the essential work of 2018 and beyond, to ensure that open infrastructure is truly a viable path for operators.

  
Barcelona, Spain
October 25-28, 2016

The Must-Attend

Open Infrastructure Event

Join the movement behind the most widely deployed open source cloud platform. Whether you are pursuing a private, hybrid or multi-cloud approach, the OpenStack Summit is the place to network, skill up and plan your cloud strategy.

  
Barcelona, Spain
October 25-28, 2016

Event Details


Cinder Always On - Reliability And Scalability Guide

Cinder (OpenStack Block Storage project) can be found in >80% of OpenStack deployments. Configuring it to be robust, resilient and fast is important. However considering its high customizability, such as choice of deployment architecture, volume backend or backup backend, an always on Cinder is not a simple goal to achieve.

In this talk we will explain how Cinder can be deployed in ways guaranteeing increased reliability and performance, as close as possible to "always on". We will walk you through latest innovations that are letting you keep your control plane and data plane up during upgrades, increased load or when experiencing breakdowns. These features include:

  • cinder-volume service in A/A mode
  • rolling upgrades support
  • volume replication
  • volume migration

We will also share insight on the improvements in these matters that are planned for the future cycles.


What can I expect to learn?

Attendees should walk out from the session aware of presence of various Cinder features that increase its control and data plane availability and with knowledge how to use them correctly for different tasks.

Wednesday, October 26, 12:15pm-12:55pm
Level: Intermediate
Red Hat, Software Engineer
Michał is software engineer working at Red Hat, engaged in OpenStack-related activities since Folsom release. Through Newton, Ocata and Pike cycles he was serving the OpenStack community as a core reviewer in Cinder, where he focused on control plane availability, scalability and upgradability. Now he's cracking similar problems in Kuryr project. His professional interests are HA... FULL PROFILE
Red Hat, Inc.
Cinder Core and Principal Software engineer at Red Hat contributing to OpenStack's Block Storage Service. Previous experience includes Artificial Intelligence, Embedded Systems and High Availability mobile payment platforms. Besides leading the effort to support Active-Active High Availability configurations in Cinder, he's also been working during the N cycle on removing DB access races... FULL PROFILE