SREcon23 Asia/Pacific
2023-06-14..2023-06-16
Singapore, Singapore
as the organisers put it
SREcon is a gathering of engineers who care deeply about site reliability, systems engineering, and working with complex distributed systems at scale. SREcon strives to challenge both those new to the profession as well as those who have been involved in it for decades. The conference has a culture of critical thought, deep technical insights, continuous improvement, and innovation. SREcon23 Asia/Pacific will be held 14–16 June, 2023 at the Suntec Singapore International Convention Centre in Singapore in
who it's for
site reliability engineers, platform engineers, observability engineers, incident response engineers, engineering managers, cloud infrastructure engineers, machine learning engineers
topics
AWS and Kubernetes at scale; Prometheus for MLOps observability; eBPF production debugging; Linux kernel upgrade automation; real-time ML platform design; battery lifecycle monitoring IoT; domain security and DNS hardening; declarative push-to-pull deployment; autonomous server diagnostics; GKE on spot instances; adaptive distributed tracing; production load testing automation
| title | author | length |
|---|---|---|
| How the Sony PlayStation Network Does SRE | Suefuji Yu, Miyahara Yuya | 41m |
PlayStation Network runs on AWS and Kubernetes, uses production game-day and load tests tied to PS5 sales/logistics, and shifts 24/7 monitoring in-house… | ||
| Unleashing Generative AI: Improving Developer Productivity in SRE | Sandeep Hooda | 36m |
Experiments use GitHub Copilot and ChatGPT (also Bard, CodeWhisperer, TabNine) to auto-complete code, suggest optimizations, fix bugs, generate unit tests and… | ||
| Patterns, Not Categories: Learning Across Incidents | Tanner Lund | 45m |
Argues that category counts and statistical bucketing often fail to produce actionable fixes, citing a 2017 Microsoft cross-division analysis that collapses… | ||
| Observability in the MLOps Lifecycle with Prometheus | Shivay Lamba | 24m |
Shows concrete instrumentation: a FastAPI model served in Kubernetes with the Prometheus operator and a service monitor, a Grafana dashboard JSON that plots… | ||
| Towards Zero Carbon: Implementing Sustainable Battery Lifecycle... | David Cesarano, Fanjing Meng | 38m |
Deployed production system monitors 160 batteries across a China data center (also piloted in Hersley UK), ingesting IoT sensor streams for voltage, current… | ||
| Leveraging Analytics for Technical Efficiency and Enhanced User Experience | Muskan Prajapati, Renisha Fernandes | 19m |
Describes three concrete systems: Outage Management Service (OMS) that is ML trained on past incidents to auto-detect, correlate outage events, run health… | ||
| LiveMLP: ML Platform for Assisting Contact Center Agents in Real-Time | Aashraya Sachdeva | 32m |
A real time ML platform is built to attach stateful workflows to each call, route per-intelligence processors via a scheduler + supervisor, and keep latency… | ||
| How Safe Is Your Domain? | Michael Kehoe | 19m |
Survey of 929 top domains finds zero following all domain best practices; only 5% enable DNSSEC, 25% use multiple DNS providers, 68% publish SPF and 58%… | ||
| From Push to Pull: Managing Mutable Infrastructure at a Global Scale | Holly Mooneyham | 40m |
A push-to-pull migration replaces Capistrano/Ansible/Jenkins pipelines with an eventually consistent, declarative system supporting ~5,000 hosts across 12+… | ||
| Autonomous Automation: How Cloudflare Handles Server Diagnostics... | Jet Mariscal | 19m |
Cloudflare runs an autonomous system called Phoenix that discovers servers in repair across 285+ PoPs in 100 countries, boots a custom Linux image to run… | ||
| Real World Debugging with eBPF | Zhichuan Liang | 46m |
Uses eBPF (implemented with bpftrace) to attach uprobes to Go binaries, compute per-goroutine timing by reading the runtime G pointer from FS-8 and struct… | ||
| An SRE Guide to Linux Kernel Upgrades | Ignat Korchagin | 34m |
Explains that Linux kernel bugfix releases arrive weekly and often matter: on the 5.15 branch there are 116 bugfix releases with 59 over 100 commits, 21 over… | ||
| Taming Spiky Log Volumes: Maintaining Real-Time Log Accessibility with Kaldb | Suman Karumuri | 40m |
Logs spike by 10x increase and cause minutes-to-hours (sometimes over a day) of lag; Slack/airbnb measured freshness SLAs around 50–70% before remediation. The… | ||
| Better Observability with No Code Changes | Tyler Benson | 21m |
Shows how to add meaningful Java tracing without code edits by using the OpenTelemetry Java agent plus a small tool and concrete heuristics. Demonstration uses… | ||
| The Secret Weapon for a Successful SRE Career - And It's Not What You Think! | Luke Mundy | 44m |
Claims that the career multiplier is deliberate self-awareness, not technical chops, demonstrated with a reusable practice: a simple emotion retro journal to… | ||
| SRE Engagement Model Transition in Building and Expanding SRE Team | Shimpei Sasano, Ryotaro Takeda | 18m |
SRE engagement model evolves from Launch, Specialization, Expansion to support a 400‑person org and 20 teams by building JDEP on Google Cloud with GKE, Google… | ||
| Untangling the Tangled Cloud | Joshua Fox | 43m |
Practical method for organizing cloud accounts by measuring actual inter-project dependencies rather than handwaving principles: an open-source tool called… | ||
| Functional Resonance Analysis: Diagramming Your System | Tanner Lund | 20m |
Functional Resonance Analysis diagrams systems as functions (hexagons) with explicit inputs → outputs, consumable resources and controls, then ties outputs… | ||
| Start Small, Scale Big: Building and Scaling Platforms and SRE Culture... | Yash Shanker Srivastava | 42m |
Starts small with three microservices and five engineers, then platformizes infrastructure as reusable Terraform modules, moves from Elastic Beanstalk then… | ||
| Cultivating Accountability and Resilience | Sandeep Hooda | 18m |
DBS presents a concrete framework called AAI (Awareness, Acceptance, Intention) inside an ABCD and E cultural shift that emphasizes forward-looking… | ||
| Finding the Needle in the Haystack: Predicting Storage Device Failures in... | Fanjing Meng, David Cesarano | 31m |
Claims a practical, multi-phase active sampler plus learning pipeline that cuts raw telemetry by sampling high‑risk devices and retrains models on demand… | ||
| Lessons Learned Running GKE Clusters on Spot Instances | Olga Mirensky | 21m |
Non‑prod clusters move to Spot for up to ~90% discounts and encounter two surprises: GKE gives only 25s SIGTERM / 5s kubelet for preemption so apps must finish… | ||
| Are We All on the Same Page? Let's Fix That | Luis Mineiro | 32m |
Claim: a webhook-style handler called Adaptive Paging ingests alerts, queries recent OpenTelemetry traces, traverses causal child spans looking for… | ||
| Humane On-call | Martin Barry | 22m |
Argues on-call needs concrete policies: treat fatigue like alcohol with fatigue management and recovery windows, expand rotation pools and recruit for on-call… | ||
| Giving Away Your Secrets: Opening Metrics Up to Users | Alexander Ananiadis | 38m |
Bloomberg shares about 200 metrics and publishes roughly 1 billion datapoints a day (peaks ~1M/min) by ingesting component metrics into a Prometheus-like… | ||
| From "Keeping the Lights On" to "Designing the LEDs": A Detailed Review... | Ian David Hamilton, Sriram Subramanian | 43m |
Claims a three‑year transformation of 500+ production engineers into SREs with a defined North Star tenant framework, an internal SRE certification, and… | ||
| Fighting Financial Crimes as an SRE | Anisha Manoharan | 40m |
Concrete claim: SREs can stop fraud by wiring log collection, detection and automated response on AWS. The talk shows a working pipeline using CloudTrail + VPC… | ||
| Beyond Observability - Aligning Technology Performance to Business Outcomes | Stephen Townshend | 21m |
Claim: extend observability to monitor people, processes and business outcomes, not just tech. Uses a practical reliability benchmarking process run with teams… | ||
| What Is Linux Kernel Keystore and Why You Should Use It in Your Next... | Ignat Korchagin | 41m |
Linux kernel keystore stores cryptographic material as kernel objects so keys never touch user space and key lifetime binds to keyrings… | ||
| Multicloud and the Chamber of Secrets | Michael Kehoe | 20m |
A multi-cloud secret inventory initially requires months of manual work across roughly 15 secret types, so Confluent automates discovery with Divi Cloud and… | ||
| Hold My Beer - Load Testing. In Production. On Autopilot. | Slava Antonenko | 33m |
Outbrain runs production load tests automatically for eight years using a homegrown service called Tulatar load test automation Runner that shifts real user… | ||
| Performance Testing in Keptn Using K6 | Jainam Shah | 18m |
Keptn runs K6 load tests as short-lived Kubernetes Jobs via the Keptn Job Executor Service, using a k6 Docker image and k6 run to produce pass/fail exit codes… | ||
| Mastering Chaos: Achieving Fault Tolerance with Observability-Driven... | Harjot Gill, Hardik Shingala | 40m |
Aperture is an open‑source control plane plus data‑plane agent that enforces observability‑driven load shedding using Aperture agent sidecar decisions… | ||
| Distributed Tracing: Adaptive and Telemetry-Based Approach for Effective... | Susobhit Panigrahi | 13m |
Claims an adaptive tracing layer that combines head+tail sampling with a density‑based clustering sampler, using feature vectors (operation path, service name… | ||
| Challenges of Managing Real-Time Financial Market Data Storage | Kiran Kasichayanula, Nishith Nedungadi | 42m |
Bloomberg migrates raw and normalized feed files from local disks to private S3-style object storage using boto3, journaling ~300 billion messages/day (~100… | ||
| Transformation Journey of E2E Customer Flow Testing... | Ananth Jayaraman, Rex Pravin L | 29m |
PayPal converts its release E2E test harness into a global synthetic-monitoring system that runs real transactions with test accounts from external agents… | ||
| The Only Constant Is Change: Lessons from a 25 Year SRE Career | Andrew Ryan | 52m |
Fourteen concrete lessons cover career moves, hands-on fixes and what to learn next: reliability work centers on three skill areas people project technical… | ||
| nothing matches | ||