The CoreSight framework available in the Linux kernel has recently been integrated with the standard Perf trace system, making HW assisted tracing on ARM systems accessible to developers working on a wide spectrum of products. This presentation will start by giving a brief overview of the CoreSight technology itself before presenting the current solution, from trace collection in kernel space to off system trace decoding. To help with the latter part the Open CoreSight Decoding Library (openCSD) is introduced. OpenCSD is an open source library assisting with the decoding of collected trace data. We will see how it is used with the existing perf tools to provide an end-to-end solution for CoreSight trace decoding. The presentation will conclude with trace acquisition and decoding scenarios, along with tips on how to interpret trace information rendered by the perf tools.
**Title: Community 3.0**
The history of open source is littered with incredible communities: thousands of people connected around the world building new technology and innovating. We can do better though. We are a facing a new era of challenges and opportunities for collaboration at a global level. In this presentation from Jono Bacon, he will explain how we can build a new generation of communities that are more efficient and more productive than ever before.
The keynote will cover how community has evolved over the years, the structure of building powerful technical and open source communities, building workflow and on-ramps, building growth, and the balance between company and community relations. All of this will be wrapped up in his trademark loose and entertaining style.
Previously Director of Community at Canonical, GitHub, XPRIZE, and OpenAdvantage. Advisor to organizations includingAlienVault, Open Networking Foundation, Open Cloud Consortium, Mycroft, and others. Wrote the critically acclaimed The Art of Community, founder of the Community Leadership Summit and global CLSx events, and prominent leader in community leadership, strategy, and execution featured on CNN, .NET, Forbes, Linux Format, and elsewhere. Founder of Jono Bacon Consulting that provides community strategy, management, and workflow consultancy for Fortune 500 companies, startups, and government across the globe.
Time Sensitive Networking (TSN) is a set of protocols and extensions that allow precise control of traffic latencies over standard Ethernet and is of growing importance in Automotive, Industrial, and Professional Audio/Video domains. This talk provides an overview of the topic and will include a dialog to help set priorities and next steps for work in this area with other interested groups.
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.
LAS16-412 96Boards Openhours
Speaker: Robert Wolff
★ Session Summary ★
96Boards will be hosting Openhours live from Linaro Connect! Join us in person or remotely to talk about all things 96Boards related.
You may think OpenDataPlane and DPDK are somewhat equivalent. But they are not. OpenDataPlane is about Software Defined Dataplanes while DPDK is a Software Dataplane. A Software Defined Dataplane can control a hardware only Dataplane in a way that packets can go from input port to output port without reaching a CPU core. With Software Dataplanes , all packets have to reach a CPU core. As a result, one vendor could leverage a Software Defined Dataplane to build a 100Tbps network box while it is not possible with a Software Dataplane.
This is a discussion on various methods put forward to reduce the size of Linux kernel and user space binaries to make them suitable for small IoT applications, ranging from low hanging fruits to more daring approaches. Results from on-going work will also be presented.