LISA19
who it's for
kubernetes operators, site reliability engineers, platform engineers, observability engineers, security engineers, infrastructure engineers
topics
kubernetes control plane internals; containerized databases and stateful workloads; multi-architecture container images; Kubernetes CI/CD with Flux and Kaniko; automated canary analysis; TLS at scale for Kubernetes services; distributed round robin scheduler with etcd; columnar event stores for logs and traces; multi-GPU time-series processing; incident command system for production incidents; DDoS attack anatomy and mitigation; vulnerability scanning for sysadmins
| title | author | length |
|---|---|---|
| The Container Operator's Manual | Alice Goldfuss | 38m |
Production experience includes running containers since 2015, Dockerizing Cassandra and operating a Kubernetes platform for GitHub, and that leads to four… | ||
| In Search of Security Shangri-la | Rich Smith | 46m |
Argues the security industry profits from fear while underdelivering, and shows concrete alternatives: replaces internal phishing click-rate metrics with… | ||
| Fuzzy Lines: Aligning Teams to Monitor Your Application Ecosystem | Kim Schlesinger, Sarah Zelechoski | 40m |
Shows a concrete frontline playbook: shared monitoring with Datadog dashboards, agreed ownership boundaries, shared Slack channels and weekly syncs, and… | ||
| How Math, Science, and Star Trek Help Us Understand the Value of Team Diversity | Fredric Mitchell | 41m |
Argues that diverse teams outperform on hard problems and cites the mathematical diversity prediction theorem (group error = average error − diversity of… | ||
| Deep Dive into Kubernetes Internals for Builders and Operators | Jérôme Petazzoni | 44m |
Builds a one‑node cluster from binaries: etcd, kube-apiserver, controller-manager, scheduler are started, then a deployment (nginx, three replicas) creates a… | ||
| Multi-GPU Accelerated Processing of Time-Series Data of Huge Academic | Ruo Ando | 42m |
Operational deployment ties an Elastic Stack + Splunk pipeline to a DGX-1 multi‑GPU box and targets PaloAlto‑7080 session logs; processing a 729 GB test dump… | ||
| Wide Event Analytics | Igor Wiedler | 29m |
Argues for treating logs as structured events, ingesting them (Kafka, Avro/protobuf) into a columnar event store so top-K, high‑cardinality group-bys run at… | ||
| Earthquakes, Forest Fires, and Your Next Production Incident | Alex Hidalgo | 39m |
A history of the Incident Command System traces back to the 1970 Laguna Fire (175,000+ acres, 382 homes lost, 16 dead) and shows how a standardized response… | ||
| Let Your Software Supply Chain Ride with Kubernetes CI/CD | Ricardo Aravena | 40m |
Practical survey of Kubernetes CI/CD that names the exact tools used, the gaps found, and concrete hardening steps: real production setup running Jenkins… | ||
| Token Up: Keeping Hands out of the Cookie Jar | Erin Browning | 31m |
Web session tokens should avoid localStorage and live in cookies scoped to subdomains with HttpOnly and Secure flags, and set SameSite=strict where possible… | ||
| Multi-Architecture Container Images: Why Bother, and How To | Lisa Seelye | 38m |
Demonstrates how to build and publish a single image name that serves both amd64 and arm64 by building per-architecture images, editing their JSON config to… | ||
| Storytelling for Engineers | Bradley Shively | 31m |
Claims that applying a simple storytelling framework to engineering communication increases understanding, voluntary compliance, and memory, and reduces… | ||
| Off the Beaten Path: Moving Observability Focus from Your Service to Your Customer | Mohit Suley | 30m |
Argues for shifting observability from infrastructure metrics to direct customer signals, showing concrete results: enabling W3C Network Error Logging reveals… | ||
| Pulling the Puppet Strings with Ansible | Brian J. Atkisson | 36m |
Red Hat IT describes migrating from CFEngine and a monolithic Puppet estate into Ansible since 2014, abandoning Puppet for new RHEL7/8 systems after wrestling… | ||
| Enabling Invisible Infrastructure Upgrades with Automated Canary Analysis | Adam McKenna | 34m |
Pinterest describes a production canary pipeline that upgrades OS, runtimes and container images by comparing a control cluster to a canary and running… | ||
| Pardon the Interposition—Modifying and Improving Software Behavior with Interposers | Danny Chen | 36m |
Interposers change program behavior at runtime using LD_PRELOAD and runtime symbol lookup like dlsym(RTLD_NEXT) to wrap C stubs for syscalls and libc… | ||
| Network Fault Finding System: Packet Loss Triangulation | Jose Leitao, Daniel Rodriguez | 29m |
An open source proof of concept called ffs actively maps ECMP paths with double traceroute and runs UDP iperf link quality tests from distributed pinger agents… | ||
| GitOps, an Elegant Tool for Hybrid Cloud Kubernetes | Ryan Cook | 32m |
Demonstrates GitOps with Argo CD managing templated Kubernetes manifests (Helm, Kustomize) across three clusters (US East1, East2, Oregon) and CloudFlare… | ||
| Ops on the Edge of Democracy | Chris Alfano | 40m |
Over six years of community work produces an open source classroom platform called Slate open source platform that handles SSO, blogging, progress reports and… | ||
| Linux Systems Performance | Brendan Gregg | 41m |
An application shows a claimed 3x speedup; root cause analysis proves it: IPC 0.56 vs 1.5 (container host runs three times more instructions per cycle), LLC… | ||
| Our Journey of Implementing TLS at Scale for Services on Kubernetes | Tilottama Gaat, Akshay Chitneni | 24m |
Describes implementing TLS for 40+ microservices on Kubernetes using Diploma (Vault-based CA) to issue certs and Chancellor (Kubernetes controller) to disburse… | ||
| Creating a Distributed Round Robin Scheduler with Etcd | Eric Chlebek | 38m |
Built a distributed round robin scheduler on top of etcd using leases and watchers and embedded etcd in a Go service, avoiding a single leader and instead… | ||
| The Challenges of Managing Open Source Infrastructure at Bloomberg | Andrew Terng | 30m |
Telemetry as a Service handles over 6M metrics/sec and ~120 TB of logs daily, so decisions focus on scale and failures: Kafka for ingestion, MetricTank as a… | ||
| Kubernetes the Very Hard Way | Laurent Bernaille | 41m |
Datadog runs tens of Kubernetes clusters up to 2,000 nodes and describes control-plane design changes: separate etcd, API, scheduler and controller pools; use… | ||
| Anatomy of a DDoS | Janna Hilferty | 37m |
Shows how attackers build botnets, how DDoS tools and mitigations actually behave, and what law enforcement achieved: memcached reflection hits 1.3 TB/s… | ||
| Expect the Unexpected! A Method for Handling Unplanned Work | Dan O'Boyle, Brian Artschwager | 38m |
Stack Overflow’s team uses an opinionated, repeatable Kanban cadence called a cycle of villainy: weekly meta/start/end meetings, strict lanes (new business →… | ||
| Expand Contract Pattern for Continuous Delivery of Databases | Leena S N | 30m |
Makes large schema changes safe and reversible by running old and new implementations in parallel, migrating data gradually, and then removing the legacy… | ||
| Sub-Region Failure: How to Handle the Partial Loss of a Data Center | Joe Gasperetti, Yang Xia | 27m |
Facebook claims a single failed switchboard should never force a full-region drain and proves it by choosing the switchboard fault domain, encoding per-service… | ||
| Distributed Sys Teams | Sri Ray | 38m |
Advocates hiring worldwide and treating people like distributed infrastructure, citing eight years remote experience and Fastly’s 65 points of presence (Mar 31… | ||
| Lightning Talks | Elizabeth K. Joseph, Paige Bernier, Amiya Adwitiya, Jainam Shah, Denise Yu, Michael Smith | 51m |
Twenty-minute rapid-fire claims and demos: a 20-year Linux-on-mainframe history with free Linux VMs on z/architecture and KVM support; a hiring postmortem of… | ||
| Depression Memes for Devops Teens: Self-Care for Server Janitors and Other Humans | Anirudh Ra | 38m |
Claims lived neurodivergence (autism, ADHD) and childhood trauma shape persistent burnout despite unlimited PTO and using short-term disability three times in… | ||
| How to Have an Operational Incident (A Crash Course) | Courtney Eckhardt | 28m |
A concrete minimum viable incident response: monitoring and alerting (confidence often ~60%), a single, publicized chat‑ops or hotline that reaches a… | ||
| Containerizing Your Monolith | Jano Gonzalez | 40m |
SoundCloud containerizes a Rails 2 monolith onto Kubernetes, moving from bare metal to a single delivery pipeline and unified infra. The process uses Docker… | ||
| Jupyter Notebooks for Ops | Derek Arnold | 24m |
Shows how Jupyter Notebooks become runnable ops tooling: live Python via the IPython kernel, data pulls with requests + pandas and charts with matplotlib… | ||
| Sysadmins' Introduction to Vulnerability Scanning | Tabitha Sable | 41m |
Argues that ops participation turns noisy scanner output into actionable work by teaching how to read reports, validate findings, and prioritize by attacker… | ||
| Testing for the Terrified: How to Write Tests, Conquer Guilt, and Level Up | Frances Hocutt | 38m |
Uses Python and pytest to write tests live for a small wrapper script, exercising the build_command function, turning failing assertions into passing ones… | ||
| What Connections Can Teach Us about Postmortems | Chastity Blackwell | 32m |
Argues that using James Burke’s Connections techniques turns dense postmortems into usable lessons by highlighting surprising connections (e.g., how unrelated… | ||
| Level Up Your Career with Soft Skills | Yoz Grahame | 38m |
Argues that interpersonal skills deliver more team value than solo technical brilliance, showing lone‑wolf = technical debt from code only they understand… | ||
| Blameless Incidents: Learning from Failure at Scale | Chip Turner | 37m |
Facebook runs a blameless incident program that trains every engineer in week two of bootcamp, classifies outages as SEV 0–4 (0 worst), and uses a central Site… | ||
| Fast, Safe, and Reliable: The Future of Configuration | Qui Nguyen | 25m |
Yelp builds a file-backed config system that dynamically reloads constants so services update without redeploys; configs live in a serf configs repo and reach… | ||
| POST No AWS Bills: Cloud Cost Optimization without APIs | Corey Quinn | 42m |
Claims that off‑the‑shelf cloud cost tools fail to capture real business insight, backed by hands‑on experiments: a netcat + dd experiment exposes… | ||
| When /bin/sh Attacks: Revisiting "Automate All the Things" | J. Paul Reed | 42m |
Argues that automation often hides failures and erodes operator skill: manual skills deteriorate if automation runs tasks for months, auto-scaling and… | ||
| Why Are Distributed Systems So Hard? | Denise Yu | 33m |
Explains why partitions are inevitable, cites Google data showing 5 rack failures, 3 router failures, 8 network maintenances in a cluster’s first year, and… | ||
| nothing matches | ||