Observability: case studies over time¶
70 case studies across 25 events, oldest first. Generated by
wiki find "observability"; each moment links to where the talk discusses it.
Organizations: A. Grabner, Affirmed Networks, Alibaba, Amgen, Bloomberg, Branch Metrics, Calyptia, Cortex, Dash0, DigitalOcean, Etsy, Fluent Bit, GitLab, Google, Grafana, Grafana Labs, HashiCorp, Heroku, Honeycomb, Honeycomb.io, Infobip, Intuit, Itaú Unibanco, JD.COM, LinkedIn, Lyft, Murphy Chen, NVIDIA, Netflix, OpenTelemetry Network, PingCAP, Planet, Red Hat, Salesforce, Shopify, Splunk, Spotify, Uber, Usabilla, Weaveworks, eBay
2017 · KubeCon + CloudNativeCon North America 2017 (Austin)¶
Would You Like Some Tracing With Your Monitoring? - Yuri Shkuro, Uber Technologies — Uber¶
Uber explains how it combines distributed tracing with monitoring, drawing on its experience building Jaeger.
2018 · KubeCon + CloudNativeCon China 2018 (Shanghai)¶
Kube-Liveboard: Make Your Cluster Visible - Xinkun Xu, JD.COM — JD.COM¶
JD.COM presents Kube-Liveboard, a tool it built to make its Kubernetes clusters visible.
Canary Deployment With Prometheus - Andrey Markelov, Infobip — Infobip¶
Infobip shows how it runs canary deployments using Prometheus metrics.
2018 · KubeCon + CloudNativeCon Europe 2018 (Copenhagen)¶
How We Used Jaeger and Prometheus to Deliver Lightning-Fast User Queries - Bryan Boreham¶
Lightning Talk: What I Wish I’d Known about Fluentd with Kubernetes - Bryan Boreham, Weaveworks — Weaveworks¶
Feeding Realworld Data into Prometheus Microservice Apps on Kubernetes - Burkhard Noltensmeier¶
Shows how real-world data was fed into Prometheus for monitoring microservice applications running on Kubernetes.
Federated Prometheus Monitoring at Scale - Nandhakumar Venkatachalam & LungChih Tung¶
2018 · KubeCon + CloudNativeCon North America 2018 (Seattle)¶
Instrumenting and Scaling Cloud-Native Databases with Envoy - Daniel Hochman, Lyft — Lyft¶
Lyft shows how it uses Envoy to instrument and scale its cloud-native databases.
Kubernetes and The GitOps Face-Off - Ricardo Aravena & Javeria Khan, Branch Metrics — Branch Metrics¶
Branch Metrics compares GitOps approaches on Kubernetes based on its own experience.
Adopting Prometheus the Hard Way - Tim Simmons, DigitalOcean — DigitalOcean¶
2019 · KubeCon + CloudNativeCon China 2019 (Shanghai)¶
Real World Architecture - Building a Global Cross-Cloud Monitoring... Dominic Green & Yifan Zhao¶
2019 · KubeCon + CloudNativeCon Europe 2019 (Barcelona)¶
From New Cluster to Insight. Deploying Monitoring and Logging to Kubernetes - Eddie Zaneski¶
M3 and Prometheus, Monitoring at Planet Scale for Everyone - Rob Skillington, Uber — Planet, Uber¶
2019 · KubeCon + CloudNativeCon North America 2019 (San Diego)¶
Lightning Talk: How the Observability Team at Spotify Radically Decreased... Lauren Muhlhauser — Spotify¶
Spotify's observability team describes how it radically decreased observability costs or usage.
Envoy on Fire: A Practical Look at Debugging a Service Mesh - Lita Cho & Ryan Cox, Lyft — Lyft¶
Lyft shares how it debugs Envoy and its service mesh in production.
From Issue to PR Merged: A Fluentd “Tail” - Jordan Hamel, Amgen — Amgen¶
2020 · KubeCon + CloudNativeCon Europe 2020 - Virtual¶
Observability at Scale: Running OpenTelemetry Across an Enterprise - Jonah Back & Kranti Vikram¶
Migrating to OpenTelemetry From a Custom Distributed Tracing Pipeline - Francis Bogsanyi, Shopify — Shopify¶
Shopify describes migrating from a custom distributed tracing pipeline to OpenTelemetry.
Scaling Prometheus: How We Got Some Thanos Into Cortex - Thor Hansen, HashiCorp & Marco Pracucci — HashiCorp¶
Monitoring GPUs at Scale for AI/ML and HPC Clusters - Bharti L Agrawal, NVIDIA — NVIDIA¶
Stateless Fluentd with Kafka - Steven McDonald, Usabilla — Usabilla¶
Usabilla describes running a stateless Fluentd logging pipeline with Kafka.
2020 · KubeCon + CloudNativeCon North America 2020 - Virtual¶
Observability Brings Clarity in 5G World - Yamini Sridaran & Praveen George, Affirmed Networks — Affirmed Networks¶
Affirmed Networks describes how it applies observability to run its 5G network workloads.
Improved TiKV Observability: How We Trace Events under Nanoseconds Latency- Wish Shi & Zhenchi Zhong — PingCAP¶
PingCAP engineers describe how they improved TiKV observability to trace events at nanosecond latency.
Sponsored Lightning Talk: Why You Need Observability to Adopt Kubernetes at Scale - Shreyans Parekh¶
An SLO-Driven Approach to Enhance Kubernetes Cluster Reliability - Qian Ding & Cong Chen¶
Speakers describe an SLO-driven approach to improving the reliability of their Kubernetes clusters.
2021 · KubeCon + CloudNativeCon + Open Source Summit China 2021¶
Best Practice: DNS Failure Observability and Diagnosis in Kubernetes - Yuning Xie, Alibaba — Alibaba¶
Alibaba shares its best practices for observing and diagnosing DNS failures in its Kubernetes clusters.
2021 · KubeCon + CloudNativeCon Europe 2021¶
How We are Dealing with Metrics at Scale on GitLab.com - Andrew Newdigate, GitLab — GitLab¶
GitLab explains how it handles metrics at scale on GitLab.com.
Building a Community: How Cortex Went from a Vendor Project to a Community - Goutham Veeramachaneni¶
Better Scalability & More Isolation? The Cortex “Shuffle Sharding” Story - Tom Wilkie, Grafana Labs — Grafana Labs¶
Grafana Labs tells how shuffle sharding in Cortex improved scalability and tenant isolation.
High Throughput with Low Resource Usage: A Logging Journey - Eduardo Silva, Calyptia — Calyptia¶
2022 · KubeCon + CloudNativeCon Europe 2022¶
From Monitoring to Observability: Left Shift your SLOs with Chaos - Michael Friedrich, GitLab — GitLab¶
Kubernetes Everywhere: Lessons Learned From Going Multi-Cloud - Niko Smeds, Grafana Labs — Grafana Labs¶
2022 · KubeCon + CloudNativeCon North America 2022¶
Customer Centric Observability: How Intuit Reduced Time To Detect... - Vinit Samel & Nagaraja Tantry — Intuit¶
DoorDash’s Journey From StatsD To Prometheus With 10 Million Metrics/Second - Emma Wang & Ben Raskin¶
Tamland: How GitLab.Com Uses Long-Term Monitoring Data For Capacity Forecasting. - Andrew Newdigate — GitLab¶
GitLab shows how Tamland uses long-term monitoring data to forecast capacity for GitLab.com.
2023 · KubeCon + CloudNativeCon Europe 2023¶
Multi-Cluster Observability with Service Mesh - That Is a Lot of Moving Parts!? - Ryota Sawada¶
The speaker shares their experience operating multi-cluster observability across a service mesh and the complexity involved.
Show Me the Metrics: How a Huge Bank Does Observability with Multi-Tenancy... - Inacio & Costa — Itaú Unibanco¶
A large bank describes running multi-tenant metrics observability at scale for its own teams.
Intuit’s Customer Centric Observability Journey Using AIOps - Vigith Maurice & Amit Kalamkar, Intuit — Intuit¶
Continuous Profiling Your Production Kubernetes Deployments Running a... Vijay Samuel & Nick Pordash — eBay¶
Describes how continuous profiling was run on production Kubernetes deployments at scale.
Hazardous Defaults: Managing Cardinality and Performance for Your Lo... Derek Cavanaugh & Sara Moore¶
Discusses managing cardinality and performance pitfalls from hazardous defaults in logging and observability setups.
2023 · KubeCon + CloudNativeCon NA 2023¶
Journey to Becoming an OpenTelemetry Approver - Jamie Danielson, Honeycomb.io — Honeycomb.io¶
How and Why You Should Adopt and Expose OSS Interfaces Like Otel... - Daniel Hrabovcak & Shishi Chen¶
2024 · KubeCon + CloudNativeCon Europe 2024¶
From RUM to Front-End Observability with OpenTelemetry - Purvi Kanal, Honeycomb — Honeycomb¶
From UI to Storage: Unraveling the Magic of Thanos Query Processing¶
2024 · KubeCon + CloudNativeCon India 2024¶
From Three Pillars to More with OpenTelemetry - Steve Flanders, Splunk — Splunk¶
2024 · KubeCon + CloudNativeCon NA 2024 - Salt Lake City¶
From Observability to Enforcement: Lessons Learned Implementing eBPF R... A. Kapuścińska, K. Kourtis¶
From Observability to Performance - Nadia Pinaeva, Red Hat & Antonio Ojea, Google — Red Hat, Google¶
OpenTelemetry: The OpenTelemetry Hero’s Journey: Working with Open Source Observability | PLT¶
Lessons Learned Adopting OpenTelemetry at Scale - Alex Arnell, Heroku / Salesforce — Heroku, Salesforce¶
Heroku/Salesforce shares lessons learned adopting OpenTelemetry at scale.
How We Made OpenTelemetry Be Our Fitness Tracker for Your CI/CD Pipelines! - N. Woerner, A. Grabner — A. Grabner¶
Understanding How OpenTelemetry Network Uses eBPF for Network Observab... S.R. Shrivastava, J. Perry — OpenTelemetry Network¶
Watching the Watchers: How We Do Continuous Reliability at Grafana Labs - Nicole van der Hoeven — Grafana¶
2025 · KubeCon + CloudNativeCon Europe 2025 - London¶
How To Adopt OpenTelemetry in an Enterprise Where Incumbent Vendor Tools Reign Supre... Chris Weldon¶
Pushing the Limits of Prometheus at Etsy - Chris Leavoy, Etsy & Bryan Boreham, Grafana Labs — Etsy, Grafana Labs¶
2025 · KubeCon + CloudNativeCon India 2025¶
Observability at Scale With Monitoring as Code... Vipin GopalaKrishnapillai & Saiabhinay Bommakanti¶
Presents practicing observability at scale through monitoring-as-code, based on the speakers' organization's own approach.
2025 · KubeCon + CloudNativeCon North America 2025¶
Designing for Observability: From Noise To Insight - Andrea Chomiak, Dash0 — Dash0¶
Building Scalable End-to-end Latency Metrics From Distributed Trace - Kusha Maharshi, Bloomberg — Bloomberg¶
Bloomberg describes building scalable end-to-end latency metrics from distributed traces.
Making Application Rollouts Observable, Actionable and Boring - Vasudev Bongale, LinkedIn — LinkedIn¶
LinkedIn shows how it made application rollouts observable, actionable and boring.
2026 · KubeCon + CloudNativeCon + OpenInfra Summit + PyTorch Conference China 2026¶
End-to-End Observability for LLM Inference: From Token To GPU - Jared Tan, Murphy Chen & Nicole Li — Murphy Chen¶
2026 · KubeCon + CloudNativeCon Europe 2026¶
Fluent Bit V5: Pushing the Limits of Observability at Scale - Eduardo Silva¶
Is the Agent in the Room with Us Right Now? - Nick Rutigliano & Andrew Halaney, Netflix — Netflix¶
Netflix engineers share their own experience with AI agents operating in their environment and the challenges of knowing what agents are doing.
How Manual OTel Instrumentation Saves More Than Just Money - Juliano Costa & Yuri Oliveira¶
Argues that manual OTel instrumentation reduces observability cost and more, based on the speakers' own experience.
From Logs to Decisions: Autonomous AI Agents for Real-Time Kubernetes Threat R... Willem Berroubache¶
Accelerating Thanos at Scale: Faster and Cheaper Queries With Parquet - Giedrius Statkevičius¶
Preventing S3 Cost Storms: Applying Cortex’s Efficiency Lessons to I/O-Heav... A. Fishman-Lichterman — Cortex¶
Applies Cortex's lessons on preventing S3 cost spikes to I/O-heavy workloads.
2026 · KubeCon + CloudNativeCon India 2026¶
Who Watches the Watchers? From Closed Observability To... Aditi Gupta, Madhu Patel & Sandeep Kanabar¶
2026 · KubeCon + CloudNativeCon Japan 2026¶
Lessons From Five+ Years of Fluent Bit: Building a Global-Scale Observability Agent - Hiroshi Hatake — Fluent Bit¶
Hiroshi Hatake shares lessons from more than five years of building and operating Fluent Bit as a global-scale observability agent.
From Tool Calls To Context Fabric: Building AI-Native Observability for… D. Choudhary & D. Kapur¶
Repurposing OpenTelemetry Traces as Test Data: Breaking the Cost Barrier in System… Y. Fujikane¶
Describes reusing OpenTelemetry traces as test data to lower the cost of system testing.