Scheduling a BoF
It's not too late! To schedule a BoF, simply write the BoF title as well as your name and affiliation on the BoFs board located in the badge pickup area. If you have a description of your BoF you'd like posted on this Web page, please schedule your BoF on the BoF board, then send the title, the organizer's name and affiliation, and the date, time, and location of the BoF to firstname.lastname@example.org with "LISA18 BoF" in the subject line.
|ROOM||CAPACITY||7:00 pm–8:00 pm||8:00 pm–9:00 pm||9:00 pm–10:00 pm||10:00 pm–11:00 pm|
|Music Row Room 3
|20||USENIX Women in Advanced Computing (WiAC) BoF||Students and Young Professionals Meetup||Board Game Night|
|Music Row Room 4||45|
|Music Row Room 5||100||Cambridge Computer Beer and Ice Cream Social|
|ROOM||CAPACITY||7:00 pm–8:00 pm||8:00 pm–9:00 pm||9:00 pm–10:00 pm||10:00 pm–11:00 pm|
|Music Row Room 3
|20||Apache Guacamole Community Meetup||Fedora & CentOS Users and Community||GPG Key Signing BoF|
|Music Row Room 4||45||AuriStor Vendor BoF||Teradactyl Vendor BoF||Gov/Mil BoF|
|Music Row Room 5||100||Elastic Vendor BoF||Open edX: Turn Your Community into a Learning Community||50-30-25-20 Years of "X" 30 Seconds at a Time: A video of how Unix and Linux changed your life.|
|275||Lightning Talks||Bloomberg Vendor BoF|
|120||Wheel of Misfortune Hosted by Squarespace||5-Minute Horror Stories|
|120||Dragging Legacy IT into the Modern Age (By Any Means Necessary)||EFF BoF|
|ROOM||CAPACITY||8:00 pm–9:00 pm||9:00 pm–10:00 pm||10:00 pm–11:00 pm|
|Music Row Room 3
|20||Private Clouds in Research and Education||Board Game Night 2.0|
|Music Row Room 4||94||Facebook Vendor BoF|
|Music Row Room 5||100||Not Available||Google Beer and Ice Cream Vendor BoF|
Let's talk about women in advanced computing. All registered attendees—of all genders—are welcome to attend these BoFs.
Join students and young professionals to network, discuss issues in the field, and the latest happenings in the community.
Join us for some good old-fashioned board games. We'll have some on hand, but bring your own games, too!
Join us for beer, ice cream, and conversation as we get ready to start LISA18!
Join fellow members of the Apache Guacamole community for an informal meetup and general discussion. Share experiences, talk with committers/contributors, and get advice on getting started.
The AuriStor File System, a next-generation successor to IBM's AFS, is deployed around the world in more than 100 cells since May 2016. Its global file namespace (/afs), platform-agnostic file paths, online backups, and an atomic publication model have proven to be critical components of successful software and content distribution systems. AuriStorFS cells scale to hundreds of thousands of systems. The /afs global name space has survived multiple OS and processor architecture changes over more than three decades making it the perfect match for global distribution of open data sets.
The AuriStorFS security model incorporates combined-identity authentication, multi-factor authorization, and mandatory security policies. AuriStorFS permits a global name space to extend across internal, DMZ and cloud infrastructures; and to store a mix of open and restricted data.
This session will discuss the most recent updates to AuriStorFS and the native Linux kernel implementation. The session will include a demonstration consisting of:
- Containers with binary executable files stored in /afs
- Containers mounting private AFS volume for scratch space
- AuriStorFS and (k)AFS file system implementations running side-by-side Linux namespaces for /afs
AuriStorFS milestones since LISA 2017 include:
- Successful migration and replication of volumes exceeding 5.5TB. The largest production volume so far is 250TB storing hundreds of 1TB or larger files.
- Deployment of a single AuriStorFS cell spanning an internal data center, AWS and GCP with more than 25,000 nodes for distribution of software and configuration data.
- Meltdown and Spectre remediation. In response to nearly 30% performance hit from Meltdown and Spectre the AuriStor team optimized the Rx stack, Ubik database and fileserver to reduce the number of syscalls by more than 50% AES-NI, SSSE3, AVX and AVX2 Intel processor optimization of AES256-CTS-HMAC-SHA1-96 cryptographic operations for kernel cache managers reduces computation time by 64%.
- AuriStor's RX implementation has undergone a major upgrade of its flow control model. Prior implementations were based on TCP Reno Congestion Control as documented in RFC5681; and SACK behavior that was loosely modelled on RFC2018. The new RX state machine implements SACK based loss recovery as documented in RFC6675, with elements of New Reno from RFC6582 on top of TCP-style congestion control elements as documented in RFC5681. The new RX also implements RFC2861 style congestion window validation.
RX peers implementing these changes are more likely to sustain the maximum available transmission throughput while improving fairness towards competing network data flows. The improved estimation of available pipe capacity permits an increase in the default maximum window size from 60 packets (84.6 KB) to 128 packets (180.5 KB). The larger window size increases the per call theoretical maximum throughput on a 1ms RTT link from 693 mbit/sec to 1478 mbit/sec and on a 30ms RTT link from 23.1 mbit/sec to 49.39 mbit/sec.
- macOS Mojave support
- Linux native kernel AFS highlights:
- Full support of AuriStorFS protocol extensions
- IPv6 support for AuriStorFS cells
- dynamic root, @sys and @cell support
- multipage read and write support
- Acceptance into Fedora Linux Rawhide 4.19 kernel
High performance computing (HPC) environments continually test the limits of technology and require peak performance from their equipment—including storage. As the growth of data in HPC is constantly expanding, optimizing performance, increasing uptime and lowering costs become vital components to any future-looking HPC storage architecture. Furthermore, with the addition of new security requirements instituted for Controlled Unclassified Information (CUI) by recent United States presidential administrations to protect government agencies and grant research data, environments are now, or will soon be, subject to CUI data management policies compliant with NIST 800-171 guidelines. Join us to learn how the Advanced Computing Center for Research and Education (ACCRE) at Vanderbilt University scaled storage for their networked computer cluster and hear from ACCRE’s Technical Director and Lead Developer Alan Tackett. Housing over 10,000 computational cores, the ACCRE Big Data cluster is used for a wide variety of services, from supporting research across their vast campus to processing complex scientific research from data-intensive environments like CERN and providing tape backup services to multiple external partners.
Dr. Tackett will discuss the ACCRE research computing platform’s unique and internally developed file system, LStore. The session will include representatives from technology partners Teradactyl and Spectra Logic. Teradactyl specializes in software for data assurance and protection of file systems for high-performance computing and wide area networks. They also designed, built, tested and put into production custom industrial purpose-built backup appliances (PBBA) for ACCRE’s ecosystem. Spectra Logic builds some of the world’s largest storage systems, developing and delivering data storage solutions that solve the problem of short- and long-term digital preservation for business and technology professionals dealing with exponential data growth. Spectra provided ACCRE with a hybrid storage architecture that enables direct end user access to archival storage and infinite scalability. ACCRE’s new deployment has been able to reduce annual storage operating charges for their backup clients by over 50 percent.
Let's discuss how you are using (or want to use) the Elastic Stack –– whether it be for search, logging analytics, metrics, security, apm, or something else exciting.
Have you ever participated in an on-call incident? Was it stressful? The Wheel of Misfortune simulates a disaster scenario where participants role play to resolve the incident using communication skills, a bit of scripted luck, and some light-hearted humor to get things back on track.
- Tiffany Longworth — Tactical Whimsy Injection: Leveraging Fun to Get Work Done
- Scott McCarty — You're Technical Right?
- Tameika Reed — How to Pivot/You are A Brand Now/How to Read a Job Description
- Viral Parmar — Modern Identity
- Larry Gordon — Your Solutions Providers Should be doing DevOps Better
- Daniel Walsh — Introducing Buildah: Building container images using Bash.
- Julien Delange — Network observability, error detection and capacity planning at Twitter
- Coburn Watson — Don't Fear the Alarm
- Steve Mushero — Dao of Troubleshooting
- Brian A. Sebby — Improvised Lighting Talk
Open edX is a comprehensive, open source collaborative learning platform. It provides everything needed to create an e-learning solution: LMS, Authoring tool, Analytics package and mobile applications. There are currently 1800 instances of Open edX serving 40+M learners in myriad learning environments: K-12, Government & NGOs, Higher education, Vocational training, Professional training, Enterprise learning and Continuous learning.
In this BoF, we'll discuss the latest developments in the Open edX community, the latest release, and much more.
There is a broad ecosystem around Open edX, and we are happy to show how you can develop and enjoy the benefits of a learning community.
Join us for drinks, southern style bites and meet Bloomberg's software engineers and SREs. Learn about the various technology infrastructure challenges they face due to the nature of Bloomberg's business processing and delivering real-time financial information. These range from owning and operating our own datacenters around the globe, deciding which vendors to use, private vs. public cloud, and managing a mixed operating system environment (i.e., Windows, Linux, Solaris and AIX) running various workloads from real-time market data processing (we handle 100+ billion ticks on an average day) to batch processing, such as end-of-day data acquisition.
Come riff about the worst/funniest/strangest situations you've had with work. Share the lighter side of Sysadmin. Keep it short, we all have ours to tell.
Electronic Frontier Foundation
Come hang out with EFF's Systems Administrator, General Counsel, and Membership lead and ask us anything!
Not all of us get to work at flashy startups or FAANGs where every application is containerized, every line of code is shuttled through a CI/CD pipeline, and all the compute servers are a gorgeously symmetrical spine-and-leaf utopia of anonymity. This BoF is for those of us that live in the real world, with applications that are hand-fed and meticulously maintained, developers that think RCS and .bak files are sufficient for revision control, and an IT culture that struggles to justify, much less fund, modern technologies and practices.
Some topics we will discuss:
- Are on-prem datacenters going the way of the dinosaurs? Are the costs of using cloud services like AWS and GCE to replace traditional on-prem IT workloads really worth it? Does it require an “IT culture transformation” or can it be done efficiently without re-designing every app that the company runs?
- What are the barriers you face that are preventing “Self-Service IT” from becoming a thing at your company? If you’ve solved this problem, how did you do it?
- Are SaaS IT management products like ServiceNow universally terrible? Or are we just doing it wrong?
- Are NFS homedirs and project workspaces actually making it harder to transform IT, by serving as an “enabler” of legacy workflows? Does NFSv4 help?
- What pitfalls do we face, trying to introduce and encourage microservices, containers, and REST APIs to an IT culture that seems content to sit on its laurels?
If you are interested in having your GPG key signed, come to the BoF. The barrier to a signing is fairly low.
Things you need:
A GPG key. If you do not have one, then generate one in advance.
Your GPG fingerprint. If you do not know how to obtain this, read the "GnuPG Keysigning Party HOWTO”, it will explain what we are doing. Pay attention to the “List based party format” section.
ID with a photo or several ID cards if you do not have one. Drivers License, passport, etc. This is not as rigid as a CA-Cert signing, so more forms of ID are acceptable. The objective is to associate an email address with a person, not to prove who you are.
If you can manage it, send me a copy of your public key in advance, as well as any additional email addresses you have associated with it that you want signed to email@example.com so I can send a keyring to all participants at the end of the signing to make things easier. It will also make the BoF go faster.
Meet the Facebook LISA speakers, Sherry Xiao, Anirudh Ra, KC Braunschweig, Andrea Barberio, David Hendricks, and Alvaro Leiva Geisse, and chat about Open Source at Facebook