Codeless Kubernetes Observability with eBPF - OpenObservability Talks S2E01
Play • 57 min

Current observability practice is largely based on manual instrumentation, which creates a barrier to entry for many wishing to implement observability in their environment. This is especially true in Kubernetes environments and microservices architecture.

eBPF (extended Berkeley Packet Filter) is an exciting new technology for Linux kernel level instrumentation, which bears the promise of no-code instrumentation and easier observability into Kubernetes environments (alongside other benefits for networking and security).

On this episode of OpenObservability Talks we’ll host Natalie Serrino, Principal Engineer at Pixie Labs, which was recently acquired by New Relic. We’ll talk about observability in Kubernetes environments, eBPF and its use cases for observability.

We’ll also talk about Pixie, the Kubernetes-native in-cluster observability platform, and the exciting news of it being open sourced and contributed these days to CNCF under Apache 2.0 license.

Natalie is a Principal Engineer and Tech Lead at New Relic. She works on the Pixie auto-telemetry observability platform, which was acquired and open sourced by New Relic. She focuses primarily on Pixie’s data layer, including its query language, compiler, and query execution engine.

Show Notes:

  • challenges in k8s observability
  • state of instrumentation
  • automatic instrumentation
  • eBPF overview
  • eBPF vs. service mesh side cars
  • Pixie project overview
  • Pixie’s roadmap and integration plans with CNCF ecosystem
  • Netflix engineering sharing use case of eBPF
  • instrumenting with Istio
  • opensearch RC1 released
  • K8s unpredictable spend
  • logs aren't enough, need tracing - recommended article






More episodes
Clear search
Close search
Google apps
Main menu