Continuing the discussion from Linaro Connect Bangkok 2016, we discuss further experiments with Window Assisted Load Tracking (WALT, formerly WinLT) on other architectures such as x86 and with different workloads including laptop/desktop and server usecases. We propose that WALT is more accurate in tracking cpu/task utilization than PELT (which we believe is better at load rather than util tracking) and that better utilization estimation schemes can be built on top of WALT. Experiments use the new schedutil governor. Examination of individual use cases in detail as well as how to handle migration and potential caveats of a windowing scheme are discussed.
In composing RTOS-based images to run on embedded systems, there are number of different issues that come into play that are different from building a root fs for Linux. Issues such as how third-party libraries and code link with the OS, how we pull down the code, etc. Additionally, such systems may also need to support the creation of filesystem-based images. There are several options that exist today (“newt" - a tool from the Apache Mynewt project in the Apache Software Foundation; “yotta" - from ARM mbed; the Yocto Project; and more). This session will discuss required features, compare and contrast project approaches, and potential additions and changes that are needed in this space.
Cities are getting identified as smart cities based on what and how data are used to do predictive analytics. Smart City as a phrase can have a wide spectrum of meaning. But there are two key things (Data and Analytics) that ‘smart’ refers to in smart city. With IoT gaining so much market attention, brings in the power to drive the implementation. Data collection, Storage and Analytics provide so much potential. This talk will go over a sample use case scenario utilizing ODPi based Hadoop eco system and H20 visualizations for analytics.
Interconnected systems require trust between devices and service providers. To deal with this problem, several companies (ARM, Solacia, Symantec, Intercede) collaborated on the Open Trust Protocol (OTrP), which combines a secure architecture with trusted code management, using technologies proven in large scale banking and sensitive data applications on mass-market devices such as smartphones and tablets.
Being able to see the performance and power impacts of changes in a real world environment such as Android is a prerequisite to doing meaningful development on scheduler-guided frequency (or many other sensitive subsystems). The first half of this session will review setting up the tools to automate testing for performance and power in Android. The second half will cover the results of using these tests to compare the schedutil and interactive governors.
For connected embedded systems we can broadly consider security across four different areas: Security within a cloud application/platform. Lifecycle security for large deployments of embedded devices. Communication security between internet connected systems. Local device security implemented within end nodes. Each connected end node needs to support aspects of lifecycle, communication and device security according to application needs. It is not scalable (or secure or productive) to start from scratch, implementing all of these aspects for each development. It is also not a good idea to implement static, closed, proprietary security systems which rely more on “security by obscurity” than on thorough, continuous and open validation of security implementations. Developers need comprehensive and flexible SW security frameworks with strong links to MCU HW security features that enable them to efficiently implement, validate and deploy “right sized” security solutions. This session will discuss the solutions that are available today, how to reason effectively about application security requirements and opportunities to evolve embedded security solutions in the future.
OpenStack is powering the next generation of the opensource cloud on a global scale. During this presentation, we will touch on three themes, running an OpenStack based cloud in production by Gema Gomez and Andy Doan, followed by Marcin talking about the packaging and bug fixing on archives required to make that happen on AArch64. Jack He and Yibo Cai, will explain what it is like working with the the upstream project, the development environment, the current patches and what needs to be done next. Then Gema Gomez will Introduce the OpenStack Interop Working Group. Why is interoperability important for OpenStack? And What is Linaro doing to improve the interoperability of OpenStack?
This presentation will give an overview of the suite of reference security solutions developed by LHG. The solutions all have OPTEE as the secure OS running on ARM TrustZone integrated with DRMs such as Microsoft PlayReady and Google Widevine on both Linux and Android platforms. The secure video path implementation strives to use common elements across Linux and Android based solutions.