Loading…
DevConf.CZ 2019 has ended

Sign up or log in to bookmark your favorites and sync them to your phone or calendar.

E104 [clear filter]
Friday, January 25
 

9:30am CET

Not Fake News, Dev-QE collaboration is possible
Waterfall model, and tennis match between QE and Devel is so last century. We all have constraints of time, resources, budgets, people, but despite all of that we have reached a state of near nirvana between QE and Development in Networking Team. We would like to share how we achieved that. In this session we will share some practical ideas about how Development and QE can establish trust, collaboration, coordination, and help make our products more robust, and in turn help our partners and customers.

Speakers
avatar for Rashid Khan

Rashid Khan

Director, Software Engineering, RHEL Networking, Red Hat
Rashid Khan is Director of Networking. His team's responsibility include kernel networking, NM, OVS, OVN, DPDK, HW enablement (NIC RDMA). He has 25+ experience working on linux networking stack, embedded solutions, and Telco. Rashid is currently in charge of our telco solutions from... Read More →


Friday January 25, 2019 9:30am - 9:55am CET
E104

10:00am CET

Multi-Networking Kubernetes Containers with CNI
When the default Kubernetes network isn't enough for your application, the flexibility of CNI comes to the rescue. In this talk we'll cover the CNI-based Kubernetes Network Plumbing Working Group's Multi-Network specification, how it's implemented in the Multus project, and how together they enable Kubernetes applications in the multi-tenant, media-streaming, NFV, and performance-sensitive application areas. In addition, we'll cover the future direction of CNI, Multus, the multi-network specification, and how container runtimes could implement these features themselves in the future.

CNI: https://github.com/containernetworking/cni
Multus: https://github.com/intel/multus-cni
Multi-Network Spec: https://github.com/kubernetes/community/pull/2665

Speakers
avatar for Dan Williams

Dan Williams

Manager, RHEL Networking, Red Hat
Dan is leading the OVN team. He is one of the architects of the OCP networking. Previously he has worked on Network Manager and made it ubiquitous for all linux distros like RHEL, Fedora, Ubuntu, Suse, Centos. Dan also lead the development of Multus, the plugin layer for Kubes, and... Read More →


Friday January 25, 2019 10:00am - 10:50am CET
E104

11:00am CET

Can OVS-DPDK be further optimised?
This session is not about how to get more juice out of an existing OVS-DPDK deployment. But what information engineering needs to further optimize OVS-DPDK for the various business needs. We will present a framework that can be used to share deployment details which will help further optimize the OVS-DPDK datapath.

Speakers
avatar for Eelco Chaudron

Eelco Chaudron

Senior Software Engineer, Red Hat
Senior Software Engineer


Friday January 25, 2019 11:00am - 11:25am CET
E104

11:30am CET

Postcopy live-migration with vhost-user backend
This talk will start with a presentation of most commonly used method for live-migrating VMs, also known as pre-copy live migration. Specifically, it will describes what is done in DPDK's vhost-user backend to support it and what limitations it brings in the scope of high-speed networking.
Then, another method whose goal is to address limitation seen, post-copy live-migration, will be presented. The addition of its support in DPDK's vhost-user backend will be described, and its possible limitations will be addressed.
Finally, the presenter will show some benchmarks comparing performance of the two solutions, to see if post-copy method keeps its promises in the scope of NFV.

Speakers
MC

Maxime Coquelin

Software Engineer, Red Hat
Maxime is SW engineer at Red Hat, member of its networking team. He mainly contributes to DPDK project, for which he is co-maintainer for the Vhost & Virtio subsystems as well as member of the DPDK technical board.


Friday January 25, 2019 11:30am - 11:55am CET
E104

12:00pm CET

NFV - Research Trends and Market Opportunities
Network Functions Virtualization (NFV) decouples packet processing from dedicated hardware middleboxes to Virtual Network Functions (VNF) running on commercial-of-the-shelf servers. In this sense, NFV helps to provide service delivery with accelerated time-to-market and agility while reducing both capital and operational expenditure. NFV has been attracting attention from both academy and industry not only because of its technological potential, but also because of the economic opportunities around such market, which include the offering, distribution, and execution of VNFs. In this presentation, we will review the NFV market and highlight how the academia and industry have been explored this. Also, we will present some state-of-art solutions that can contribute to large adopt of NFV.

Speakers
avatar for Muriel Franco

Muriel Franco

Research Assistant, University of Zurich / CSG
Ph.D. student at the University of Zurich and a Research Assistant at the Communication Systems Group (CSG@IfI) under the supervision of Prof. Burkhard Stiller. Also, part of a work team financed by Brazilian Research Backbone (RNP/Brazil) to develop and implant a federated ecosystem... Read More →


Friday January 25, 2019 12:00pm - 12:50pm CET
E104

1:00pm CET

Declare your Linux Network state!
Various services built on top of Linux need to manage the network configuration. Each service models network entities differently and uses various APIs to change the network state, multiplying the required work.
NMState centralizes the challenges by providing a unified declarative representation of the Linux network state and allowing to modify it using the same schema. NMState also provides Ansible network modules to manage Linux systems, conforming to the same uniform schema used to control network appliances.
The talk will introduce NMState, its core capabilities, current users and roadmap, including plans for Kubevirt, oVirt, Openshift and Openstack support. Afterwards, the audience will understand the benefits of using NMState to centralize collaboration on Linux network management.

Speakers
avatar for Edward Haas

Edward Haas

Principal Software Engineer, Red Hat
Software and Networking specialist, currently focusing on virtualization and container technologies. Experienced with data path optimization and acceleration.Consider code as an art and keeping it clean as a must.
avatar for Till Maas

Till Maas

Senior Software Engineer, Red Hat
As a senior software engineer at Red Hat, Till Maas maintains the Network System Role for Ansible and works on Nmstate, a declarative network manager API.For more than 12 years, he contributes to the Fedora project in multiple areas. Currently he serves as an elected member of the... Read More →



Friday January 25, 2019 1:00pm - 1:25pm CET
E104

1:30pm CET

upstream kernel CI using patchew and TDC
The Linux kernel provides TDC, a selftest suite for the TC subsystem. Unit tests are easy to write (a small example is presented), and the self-test suite can be enhanced with plugins to allow more coverage (e.g. valgrind or kmemleak). We show the setup of patchew (https://patchew.org) to monitor the kernel netdev mailing list and launch the TDC testsuite for each single patch targeting the TC subsystem. Developers/maintainers are then notified in case of functional breakage. Attendees will be encouraged to contribute to the Linux kernel testsuite, know more about patchew and also find a quick reference of usage for TC commands.

Speakers
avatar for Davide Caratti

Davide Caratti

software engineer, Red Hat
kernel developer at Networking Services Team



Friday January 25, 2019 1:30pm - 1:55pm CET
E104

2:00pm CET

Ansible powered Network automation
Going through the use case of Red Hat IT utilizing Ansible for deploying network devices. Showing a way how to manage network devices using Ansible and code defined configuration generation. Using Ansible for enforcing standards, configuration auditing, deploying and maintaining network devices more efficiently. Leading to fully code defined network prone to human errors and misconfiguration. With all advantages of the auditable, transparent, resilient and homogeneous network.

Speakers
MM

Martin Moucka

Senior Network Engineer, RH - Brno - FBCII



Friday January 25, 2019 2:00pm - 2:50pm CET
E104

3:00pm CET

WiFi & Privacy treats: what NetworkManager can do
When a network connection is attempted, some unique identifiers must be disclosed (namely the MAC address and the DHCP Client Identifier). If they are not properly managed, it could be really easy to track a user.
After a brief overview about these unique identifiers, you will learn how to tune NetworkManager configuration in order to achieve your desired level of privacy. You will see also in which way that could affect your connections.

Speakers
avatar for Francesco Giudici

Francesco Giudici

Senior Software Engineer, Red Hat



Friday January 25, 2019 3:00pm - 3:25pm CET
E104

3:30pm CET

Firewalld Changes Coming to Your OS
Firewalld has undergone a lot of change in the past year. This talk will discuss recent and future developments with an emphasis on why they are beneficial for users. Topics include; nftables, rule priorities, testsuite improvements, NetworkManager integration.

Speakers
EG

Eric Garver

Principal Software Engineer, Red Hat


Friday January 25, 2019 3:30pm - 3:55pm CET
E104

4:00pm CET

Fight Linux fragmentation with Flatpak
Flatpak is a cross-distribution framework to build and deliver sandboxed desktop apps. My open-source project, which focuses on the integration of web-based music streaming services with Linux desktop, has struggled with Linux fragmentation for years. Finally, I switched to Flatpak packages as the sole distribution method in March 2017 and I have never looked back.

What were the reasons to retire DEB & RPM packaging? Did Flatpak come up to my expectations? What are its benefits from the developer's point of view? How to develop directly inside the sandbox? Are there any rough edges?

Speakers


Friday January 25, 2019 4:00pm - 4:25pm CET
E104

4:30pm CET

Flatpaks in Fedora - an update
At DevConf.cz last year, Fedora's efforts to create Flatpaks in Fedora infrastructure out of Fedora Packages were presented. At that point, development was far along, but the capability was not yet deployed in Fedora infrastructure. A year later, Flatpaks are being built and are available for users to install.

This session will cover:

* What has changed in the last year?
* What progress has been made at creating a Fedora-based runtime and application Flatpaks?
* How do Fedora packagers and other interested get involved?
* How do users try out the Flatpaks?
* Automation and other things currently being worked on.

Speakers
avatar for Owen Taylor

Owen Taylor

Architect, Desktop Engineering, Red Hat


Friday January 25, 2019 4:30pm - 4:55pm CET
E104

5:00pm CET

Running virtual machines in the Flatpak sandbox
A journey through the challenges of running a virtualization stack in the Flatpak sandbox with the purpose of distributing GNOME Boxes in immutable image-based operating systems such as Fedora Silverblue.

Starting from orchestrating the build of all the required components of the virtualization stack, to poking holes in the Flatpak sandbox in order to provide device passthrough, safe file sharing, and a bridged network between host and guest.

Speakers
avatar for Felipe Borges

Felipe Borges

Senior Software Engineer, Red Hat
Felipe Borges has been involved in GNOME since 2009, contributing with translation, marketing, and development. Currently contributes to various GNOME components and is the maintainer of GNOME Boxes.


Friday January 25, 2019 5:00pm - 5:25pm CET
E104

5:30pm CET

What's new in gnome-software?
gnome-software, the GNOME software center keeps improving and changing all the time. In this talk, I'll walk you through what we've been up to over the past year since last DevConf.CZ, show pictures, videos, and be available for questions and suggestions afterwards.

Speakers

Friday January 25, 2019 5:30pm - 5:55pm CET
E104
 
Saturday, January 26
 

9:00am CET

Data Science in the Open Cloud Exchange model
Have a great idea for a data science experiment but don't have the hardware to run it?  The Massachusetts Open Cloud (MOC) and Red Hat have partnered to deploy the Open Data Hub, an open source AI-as-a-Service platform, into the MOC giving you access to hardware and support required for leading edge experiments.

The MOC Infrastructure-as-a-Service platform combined with OpenShift and current data science development tools provides you with an alternative to using public clouds to execute your experiments.

The Open Data Hub currently has a number of early adopter projects running in the MOC environment and the Open Cloud Exchange model the MOC has implemented is something we are working with local parties in Czech Republic to reproduce.

Attend this talk to learn about:
  • What the Massachusetts Open Cloud and Open Cloud Exchange is
  • Current projects running in the MOC
  • Running your project in the MOC
  • How we are working with parties in Czech Republic to replicate the MOC implementation and goals

Speakers
avatar for Steven Huels

Steven Huels

Sr Director, AI Cloud Services, Red Hat
Steven Huels is a Director in the Red Hat AI Center of Excellence with responsibility for the Data Hub, the Common AI Library, Thoth, and AI Ops.
avatar for Václav Pavlín

Václav Pavlín

Architect, AI CoE, Office of the CTO, Red Hat Czech
Red Hatter for almost 6 years, working with containers for 5 years, making AI/ML simple, proud Brnonian and Czech



Saturday January 26, 2019 9:00am - 9:50am CET
E104

10:00am CET

while(1) i++ — How far can it go?
Modern day computing has us surrounded with all these 256 bit AES keys, 4096 bit RSA keys, 384 bit ECDSA keys or 448 bit Blowfish keys. The AVX-512 instructions allow for operating on 512 bits at once. It might seem that those numbers are easily within our grasp, but are they?

Speakers
PO

Pavel Odvody

Software Engineer, Red Hat
Software Engineer working for Red Hathttp://blog.quaswexort.net/


Saturday January 26, 2019 10:00am - 10:25am CET
E104

10:30am CET

Analysing differences in kernel parameters
In this session, we present the DiffKemp project - a tool for automatic
analysis of code differences between two versions of the Linux kernel. The
tool partially automates kernel option compatibility cross-check (sysctl
variables, module parameters) which makes the process of the kernel
development and deployment more efficient and reliable. The approach that we use is based on static analysis of the kernel source code, which makes sure that all program paths are covered. Moreover, we use advanced formal methods to prove an equivalence of semantics of programs even when the code is syntactically different.

Speakers
VM

Viktor Malík

Software Engineer, Red Hat


slides pdf

Saturday January 26, 2019 10:30am - 10:55am CET
E104

11:00am CET

KETCube - the Prototyping&Educational IoT Platform
KETCube is the novel modular prototyping/demo/edu IoT platform developed at KET UWB (University of West Bohemia) in Pilsen. It's primary intended is LPWAN IoT node prototyping and test-series deployment (very small footprint).
KETCube platform consists of firmware, mainBoard, a set of extension boards and industry-like documentation.

The modular design of firmware allows rapid extension development. An easy-to-develop KETCube sensor/actuator extension boards or mikroBUS(TM)-compatible sensor boards, can be connected to KETCube main board.

KETCube is released under BSD-like license (https://github.com/SmartCAMPUSZCU/KETCube-docs). The target audience are educationalists, IoT HW developers and makers. We would like to attract potential users and contributors. Max attendees: unlimited.

Speakers
JB

Jan Bělohoubek

R&D Engineer, University of West Bohemia in Pilsen



Saturday January 26, 2019 11:00am - 11:25am CET
E104

11:30am CET

Cloud native data replication strategies
This talk explains the key challenges of data replication of cloud/on-prem based Big Data clusters. To show how the replication strategies of the current storage systems (eg. Hadoop HDFS, Ceph)could be improved.

I. DATA

* What is Apache Hadoop Ozone
* main strength and vision (TLDR; multiple interfaces, not just hadoop: +s3 +posix fs).
* Explain why data replication is a key element of a cloud native storage.

II. SCIENCE

* Commonly used strategies (eg. random replication)
* What are the problems? (multiple independent node failures guarantee data loss)
* How they could be improved (larger data loss can be accepted if it has lower possibility).

This part is based on the copyset/hyperset papers but visualized and presented in a simplified way to easy to understand

Speakers
avatar for Marton Elek

Marton Elek

Engineer, Cloudera
Marton Elek is am Open Source Engineer at Cloudera. He is an Apache committer in Apache Hadoop project and PMC member of Apache Ratis. He has an experimental containerization project for Hadoop, Spark and other bigdata components which includes docker containers, and configuration... Read More →



Saturday January 26, 2019 11:30am - 11:55am CET
E104

12:00pm CET

Teaching Programming to Teenagers: A Summer Camp
Each summer, we take a group of teenagers and spend a week in mountains, teaching them programming. The camp has been going on for 20 years. We'd like to share our experiences. What have we learned? How to do such camp in a way accessible to teenagers? Can I join, or even hold my own camp? And what technologies to use?

The answer to the last question is simple: open source, of course. During the past years, we've even started developing our own tools. Let's grab them from Github and have some fun.

The talk is open to anyone, whether you're working in education or not. Come to get some inspiration. And give some, if possible – we want to learn from you and hope for a nice discussion.

Speakers
avatar for Jiri Benc

Jiri Benc

Principal Kernel Engineer, Red Hat
Jiri is a Linux kernel developer with networking background. His main focus nowadays is on network virtualization and networking solutions for cloud computing.
avatar for Marian Šámal

Marian Šámal

Developer, Revolware
Just a 16-year-old programmer doing some Linux stuff.



Saturday January 26, 2019 12:00pm - 12:25pm CET
E104

12:30pm CET

Erasure Codes in a nutshell
This session will be a great option for people who already know about Erasure codes and want to understand low-level details. The presentation will contain a high-level overview of standard EC implementations, detailed information about math and algorithms behind EC and practical examples. This session is not suitable for EC developers.

Speakers


Saturday January 26, 2019 12:30pm - 1:20pm CET
E104

1:30pm CET

Understanding TLS certificate validation errors
Last year, we asked 75 developers to validate five certificates and understand the error messages they got.

Why did or didn't they succeed? What were the most common misconceptions? What resources did people use to determine the security consequences? Can we improve the situation by creating better documentation?
In our research, we focused on error messages and documentation regarding the validation of TLS certificates. We'll present insights from the DevConf 2018 research booth, answering the questions from the previous paragraph.

We use TLS certificate validation as a real-world example to spark conversation on usable security and developer experience.
This research is a part of the academic cooperation of Red Hat and Masaryk University.

Speakers
avatar for Martin Ukrop

Martin Ukrop

researcher, teacher, Masaryk University
Passionate about usable security, user experience, teaching and experiential learning. Actively organizing educational events in the community "Instruktoři Brno". Ceaselessly fascinated by the world.



Saturday January 26, 2019 1:30pm - 2:20pm CET
E104

2:30pm CET

What is Red Hat CoreOS?
Ever heard of Atomic Host? How about Container Linux? Join Jeff Ligon and Steve Milner to learn about Red Hat's new Immutable OS: Red Hat CoreOS. We'll discuss the continuing philosophy of CoreOS Container Linux, the update mechanism of the new Red Hat CoreOS, and the what it means to be the host foundation for Openshift.

Speakers
avatar for Jeff Ligon

Jeff Ligon

Software Engineering Manager, Red Hat, Inc.
I am a manager working for the Runtimes, RHCOS, and CCOST teams at Red Hat.
avatar for Steve Milner

Steve Milner

Principal Software Engineer, Red Hat



Saturday January 26, 2019 2:30pm - 3:20pm CET
E104

3:30pm CET

Fedora CoreOS: architectural walkthrough
Fedora CoreOS is a future Fedora edition drawing from the best of Fedora Atomic Host and CoreOS Container Linux. This talk is an update from the Flock one, but will start with an overview of what Fedora CoreOS is, and how it incorporates lessons from those two operating systems into its DNA. We will then focus on the current state of Fedora CoreOS: design decisions, development, and community.

https://coreos.fedoraproject.org/
https://github.com/coreos/fedora-coreos-tracker

Speakers
avatar for Luca BRUNO

Luca BRUNO

Remote Germany
CoreOS Engineer, Rust & Go developer, enthusiast FLOSS supporter.
JL

Jonathan Lebon

Software Engineer, Red Hat Canada Ltd.



Saturday January 26, 2019 3:30pm - 4:20pm CET
E104

4:30pm CET

Fedora CoreOS Build Tooling
Fedora CoreOS is built, tested, and released differently than the operating systems from which it originated, Fedora Atomic Host and CoreOS Container Linux. This talk covers a very brief overview of how CL and FAH images were previously built and how the Fedora CoreOS build system, CoreOS Assembler, improves upon them. It discusses how CoreOS Assembler aims to unify the developer and production build processes and ensure reproducibility. It also covers the CoreOS Assembler developer workflow both for developing the OS and build process itself. Finally it covers what is coming next for CoreOS Assembler.
No resources required, max attendees, etc

Speakers

Saturday January 26, 2019 4:30pm - 4:55pm CET
E104

5:00pm CET

Ignition: declarative first-boot host configuration
Ignition is an early-boot node configuration tool, based on a declarative configuration format and meant to run on first boot. It is capable of partitioning disks, creating filesystems, and writing configuration entries for full initial provisioning of a Linux host.
This talk will describe design choices specific to Ignition, highlighting all the fundamental differences with traditional `cloud-init` approach. It will show how Ignition enables automated, declarative, immutable infrastructure patterns in clustered Linux deployments. Additionally it will cover Ignition architecture, internal Go patterns and initramfs integration.
* https://github.com/coreos/ignition

Speakers
avatar for Luca BRUNO

Luca BRUNO

Remote Germany
CoreOS Engineer, Rust & Go developer, enthusiast FLOSS supporter.



Saturday January 26, 2019 5:00pm - 5:25pm CET
E104
 
Sunday, January 27
 

9:00am CET

Performance Co-Pilot and Ruby
Performance Co-Pilot (PCP) is an open source framework and toolkit for monitoring and analyzing live and historical system performance. It provides high-resolution live monitoring from local or remote hosts (with optional auto-discovery) and instrumented software. PCP can be integrated with monitoring solutions like Graphite (Carbon/Whisper), InfluxDB, Zabbix or Nagios, or configured to store historical data into archive files which is a unique feature we want to take advantage from. The talk covers PCP installation, basic operating system monitoring and shows how to read internal metrics from a Ruby application via Statsd or Prometheus APIs.

Speakers
avatar for Lukáš Zapletal

Lukáš Zapletal

Software Engineer, Red Hat
The Foreman open-source project core member with focus on hardware discovery, bare-metal provisioning, non-Intel architectures, PXE and SELinux. Works in Red Hat Satellite 6 engineering team.


Sunday January 27, 2019 9:00am - 9:25am CET
E104

9:30am CET

LLDB - a new C++ debugger
LLDB is a debugger from LLVM/clang toolchain. With its relatively new LLVM codebase it provides exceptional performance while enabling convenient investigation of complex C++ debugged data structures. Its integration with clang compiler for expression parsing permits running arbitrary ad hoc C++ snippets without recompiling and restarting possibly huge C++ programs being debugged. These unique features are not available with GDB so far.

Speakers
avatar for Jan Kratochvíl

Jan Kratochvíl

LLDB and formerly GDB developer, Red Hat



Sunday January 27, 2019 9:30am - 9:55am CET
E104

10:00am CET

Modern strace
strace is a diagnostic, debugging and instructional utility for Linux.
It is used to monitor and tamper with interactions between processes and the Linux kernel, which include system calls, signal deliveries, and changes of process state.

Linux developers are usually aware of strace and use it occasionally, but their knowledge about modern strace features is often quite limited.
In this talk the maintainer of strace will describe features of modern strace and demonstrate what kinds of problems they help to solve.
The talk will raise awareness about strace, this will help Linux developers and users to gain a better understanding of strace and other tracing tools.

Speakers
avatar for Dmitry Levin

Dmitry Levin

Chief Software Architect, BaseALT
Dmitry is the co-founder and the chief software architect of BaseALT, a long time contributor to free software projects, including strace, the GNU libc, Linux kernel, Linux-PAM, and many others.Being the maintainer of strace since 2009, Dmitry gives talks about this tool for various... Read More →



Sunday January 27, 2019 10:00am - 10:50am CET
E104

11:00am CET

Reverse Engineering Binaries
Session will walk through demonstrating various ways of tracking the run time issues using binary utilities available with `binutils` package and `gdb` debugger in absence of source code, just from binary executables or libraries. This session will help the audience understand the code flow from binary files alone, backtracking and formulating the potential source code, binary is generated form. Many kind of problems like symbol resolution failure, application crashes and deviation from standard programming practices can be identified using these tools, without access to actual source code of the application. These are the foundations of hacking and cracking. Some insight into system architecture (like registers and their usage) and assembly language and programming is helpful.

Speakers
avatar for Divya Basant Kumar

Divya Basant Kumar

Senior Software Maintenance Engineer, Red Hat
Working in Toolchain and Desktop domain for 7+ years


Sunday January 27, 2019 11:00am - 11:50am CET
E104

12:00pm CET

Linux Kernel Control Group v2
Control group (cgroup) and namespace are the two major features in the Linux kernel that make containers possible. The original cgroup v1 allows different process hierarchies for different controllers. That makes it hard for different controllers to coordinate their effort together. The new cgroup v2, on the other hand, forces all the controllers to operate under a unified process hierarchy. This makes it possible to provide features that are not possible under cgroup v1.

This presentation focus on what cgroup v2 can bring to the table, the difference between cgroup v1 and v2 and their pros and cons.

Speakers
avatar for Waiman Long

Waiman Long

Principal Software Engineer, Red Hat
Principal Software EngineerWaiman Long is an experienced kernel software engineer at Red Hat, Inc. His major focus areas are kernel synchronization primitives, performance and scalability, and cgroup in the upstream Linux kernel as well as the Red Hat Enterprise Linux kernel.



Sunday January 27, 2019 12:00pm - 12:50pm CET
E104

1:00pm CET

Performance tuning of Red Hat Enterprise Linux
This session will cover the performance analysis and tuning of Red Hat Enterprise Linux(RHEL). The session will be split into 4 sections: 1.) Hardware and kernel configuration of systems running RHEL, 2.) Performance analysis of the system. 3.) Tools used to evaluate system performance and help tune the kernel for optimal performance. 4.) The actual techniques used to tune systems
RHEL with several real-word examples. The first section will cover typical hardware features of large systems and discuss the best configuration. The second section will illustrate how to determine how well a system is performing and if it can be improved. The third section will explore a variety of tools used to study system performance. The forth section will illustrate performance tuning techniques

Speakers
avatar for Larry Woodman

Larry Woodman

Larry Woodman is a senior consulting engineer at Red Hat., Red Hat
Larry Woodman is a senior consulting engineer in the RHEL kernel engineering organization. He contributes to the upstream kernel a well as the RHEL kernels. Over the past 15 years that Larry has worked in the RHEL kernel engineering group he has fixed o



Sunday January 27, 2019 1:00pm - 1:50pm CET
E104

2:00pm CET

Monsters, Ghosts, and Bugs: How to choose a kernel
Most users and developers don’t think too closely about what kernel is running, yet the kernel is a vital piece of software. There’s many choices of what kernel to run, from a well tested enterprise kernel to forward looking community distributions to running your own compiled version. Each of these options has a use case and the choice of kernel can have a big impact on your system. So how do you choose? The focus of this talk is the many ways a kernel can be maintained and what it means for consumers of that kernel. Emphasis will be given to the trade offs of features vs. security vs. ease of management and mistakes you can make when maintaining a kernel.

Speakers
avatar for Laura Abbott

Laura Abbott

Fedora Kernel Engineer, Red Hat
Laura is currently employed Red Hat as a Fedora Kernel Engineer. She thinks kernels are really cool, even when they crash. Her day-to-day work involves bug fixes, tending the Fedora kernel releases, and other development work for the benefit of Fedora.



Sunday January 27, 2019 2:00pm - 2:50pm CET
E104
 


Filter sessions
Apply filters to sessions.
  • Academic & Research
  • Activity
  • Agile / DevOps / SRE
  • Blockchain
  • Cloud and Containers
  • Community
  • Debugging / Tracing
  • Desktop
  • Developer Tools + IoT
  • Documentation
  • Fedora
  • Frontend / UI / UX
  • Immutable OS
  • Kernel
  • Lightning Talks
  • Meetup / Hackfest
  • MIcroservices
  • Middleware
  • ML / AI / Big Data
  • Networking
  • Platform / OS
  • Quality & Testing
  • Security / IdM
  • Storage / Ceph / Gluster
  • Virtualization