27:15

SREcon21 - When Linux Memory Accounting Goes Wrong

USENIX

45:15

SREcon21 - Don't Follow Leaders or "All Models Are Wrong (and So Am I)"

USENIX

24:53

SREcon21 - Let the Chaos Begin—SRE Chaos Engineering Meets Cybersecurity

USENIX

30:20

SREcon21 - What's the Cost of a Millisecond?

USENIX

12:35

SREcon21 - What To Do When SRE is Just a New Job Title?

USENIX

30:08

SREcon21 - Capacity Management for Fun & Profit

USENIX

30:21

SREcon21 - A Political Scientist's View on Site Reliability

USENIX

49:50

SREcon21 - Panel: Engineering Onboarding

USENIX

13:23

SREcon21 - Sparking Joy for Engineers with Observability

USENIX

49:36

SREcon21 - Panel: Observability

USENIX

29:03

SREcon21 - 10 Lessons Learned in 10 Years of SRE

USENIX

38:36

SREcon21 - Rethinking the SDLC

USENIX

27:32

SREcon21 - Elephant in the Blameless War Room—Accountability

USENIX

20:25

SREcon21 - How LinkedIn Performs Maintenances at Scale

USENIX

26:13

SREcon21 - Take Me Down to the Paradise City Where the Metric Is Green and Traces Are Pretty

USENIX

27:25

SREcon21 - Need for SPEED: Site Performance Efficiency, Evaluation and Decision

USENIX

30:32

SREcon21 - SLX: An Extended SLO Framework to Expedite Incident Recovery

USENIX

13:22

SREcon21 - Watching the Watchers: Generating Absent Alerts for Prometheus

USENIX

12:26

SREcon21 - A Principled Approach to Monitoring Streaming Data Infrastructure at Scale

USENIX

26:50

SREcon21 - Let's Bring System Dynamics Back to CS!

USENIX

29:49

SREcon21 - From 15,000 Database Connections to under 100—A Tech Debt Tale

USENIX

34:16

SREcon21 - MySQL and InnoDB Performance for the Rest of Us

USENIX

25:57

SREcon21 - Cache Strategies with Best Practices

USENIX

30:38

SREcon21 - Optimizing Cost and Performance with arm64

USENIX

15:42

SREcon21 - Ceci N'est Pas un CPU Load

USENIX

14:31

SREcon21 - Grand National 2021: Managing Extreme Online Demand at William Hill

USENIX

28:50

SREcon21 - Microservices above the Cloud—Designing the International Space Station for Reliability

USENIX

21:59

SREcon21 - Horizontal Data Freshness Monitoring in Complex Pipelines

USENIX

30:33

SREcon21 - How We Built Out Our SRE Department to Support over 100 Million Users for the World's 3rd

USENIX

29:54

SREcon21 - You've Lost That Process Feeling: Some Lessons from Resilience Engineering

USENIX

13:12

SREcon21 - Scaling for a Pandemic: How We Keep Ahead of Demand for Google Meet during COVID-19

USENIX

49:04

SREcon21 - DevOps Ten Years After: Review of a Failure with John Allspaw and Paul Hammond

USENIX

33:41

SREcon21 - What If the Promise of AIOps Was True?

USENIX

12:17

SREcon21 - Model Monitoring: Detecting and Analyzing Data Issues

USENIX

14:14

SREcon21 - Leveraging ML to Detect Application HotSpots [@scale, of Course!]

USENIX

28:45

SREcon21 - Demystifying Machine Learning in Production: Reasoning about a Large-Scale ML Platform

USENIX

13:02

SREcon21 - Designing an Autonomous Workbench for Data Science on AWS

USENIX

45:47

SREcon21 - Panel: OpML

USENIX

15:10

SREcon21 - When Systems Flatline—Enhancing Incident Response with Learnings from the Medical Field

USENIX

28:20

SREcon21 - Evolution of Incident Management at Slack

USENIX

14:49

SREcon21 - Hacking ML into Your Organization

USENIX

22:00

SREcon21 - Automating Performance Tuning with Machine Learning

USENIX

30:49

SREcon21 - Practical TLS Advice for Large Infrastructure

USENIX

27:36

SREcon21 - Learning More from Complex Systems

USENIX

29:37

SREcon21 - Of Mice & Elephants

USENIX

25:53

SREcon21 - User Uptime in Practice

USENIX

29:33

SREcon21 - Nothing to Recommend It: An Interactive ML Outage Fable

USENIX

26:29

SREcon21 - Improving Observability in Your Observability: Simple Tips for SREs

USENIX

44:13

SREcon21 - SRE for ML: The First 10 Years and the Next 10

USENIX

19:49

SREcon21 - Lessons Learned Using the Operator Pattern to Build a Kubernetes Platform

USENIX

27:02

SREcon21 - Nine Questions to Build Great Infrastructure Automation Pipelines

USENIX

31:15

SREcon21 - Hard Problems We Handle in Incidents but Aren't Recognized

USENIX

27:56

SREcon21 - Experiments for SRE

USENIX

30:07

SREcon21 - Reliable Data Processing with Minimal Toil

USENIX

14:55

SREcon21 - SRE "Power Words"—the Lexicon of SRE as an Industry

USENIX

14:39

SREcon21 - How Our SREs Safeguard Nanosecond Performance—at Scale—in an Environment Built to Fail

USENIX

44:37

SREcon21 - Panel: Unsolved Problems in SRE

USENIX

39:02

SREcon21 - Beyond Goldilocks Reliability

USENIX

30:20

SREcon21 - A Retrospective: Five Years Later, Was Chaos Engineering Worth It?

USENIX

18:28

SREcon21 - The Origins of USAA's Postmortem of the Week

USENIX

27:48

SREcon21 - Cache for Cash—Speeding Up Production with Kafka and MySQL binlog

USENIX

27:22

SREcon21 - Taking Control of Metrics Growth and Cardinality: Tips for Maximizing Your Observability

USENIX

32:37

SREcon21 - Games We Play to Improve Incident Response Effectiveness

USENIX

29:58

SREcon21 - Food for Thought: What Restaurants Can Teach Us about Reliability

USENIX

25:33

SREcon21 - Latency Distributions and Micro-Benchmarking to Identify and Characterize Kernel Hotspots

USENIX

23:28

SREcon21 - Trustworthy Graceful Degradation: Fault Tolerance across Service Boundaries

USENIX

19:38

SREcon21 - Spike Detection in Alert Correlation at LinkedIn

USENIX