How Continuous Profiling with Pyroscope Supercharges Kubernetes Microservices

What Is Pyroscope?

Pyroscope is an open‑source continuous profiling platform consisting of a server and agents that efficiently collect, store, and query profiling data for any language.

Profiling measures a program’s memory usage, time complexity, and function call frequency and duration, helping developers locate and fix performance bottlenecks.

Continuous Profiling

Continuous profilers analyze code‑level performance over time in production environments, quickly revealing resource‑intensive functions after new code is introduced, thereby reducing latency and cloud costs.

Available Continuous Profilers

Pyroscope

Parca

Datadog

Google Cloud Profiler

Pyroscope distinguishes itself by using a purpose‑built storage engine for fast queries and supporting language‑specific agents as well as eBPF‑based profiling.

Why Use Pyroscope?

It stores data efficiently with BadgerDB, offers low‑overhead CPU usage, and provides human‑readable profiles across many languages (Go, Python, Ruby, eBPF, Java, .NET, PHP, Rust).

Parca relies on eBPF for C, C++, Go, etc., but may produce unreadable symbols for interpreted languages like Python.

Thus, Pyroscope combines language‑specific agents with eBPF to deliver actionable, readable profiles.

Installing Pyroscope

“No matter whether you use Docker, Linux, Ruby, or Go, Pyroscope can start a server and then an agent. Its custom storage engine enables fast queries even for long‑term data.” – Pyroscope website

Use Minikube to create a Kubernetes cluster and install Pyroscope via Helm:

minikube start

helm repo add pyroscope-io https://pyroscope-io.github.io/helm-chart

helm install pyroscope pyroscope-io/pyroscope --set service.type=NodePort

helm list

kubectl get all

After confirming Pyroscope is running, integrate it with the Google microservices demo.

Integrating Pyroscope with Google Microservices Demo

Modify container images to include the Pyroscope binary, which starts the application and injects profiling.

Python Service

COPY --from=pyroscope/pyroscope:latest /usr/bin/pyroscope /usr/bin/pyroscope
CMD ["pyroscope", "exec", "python", "email_server.py"]

Build and push the image:

docker build . -t beellzrocks/emailservice:latest
docker push beellzrocks/emailservice:latest

.NET Service

COPY --from=pyroscope/pyroscope:latest /usr/bin/pyroscope /usr/bin/pyroscope
ENTRYPOINT ["pyroscope", "exec", "-spy-name", "dotnetspy", "/app/cartservice"]

Build and push the image similarly.

Go Service

import (
  "github.com/pyroscope-io/pyroscope/pkg/agent/profiler"
)

func main() {
  pyroscope.Start(pyroscope.Config{
    ApplicationName: os.Getenv("APPLICATION_NAME"),
    ServerAddress:   os.Getenv("SERVER_ADDRESS"),
  })
  // application code here
}

After rebuilding the Go image, update the Kubernetes manifests to use the new images and add the required capabilities and environment variables:

containers:
  - name: server
    env:
    - name: PYROSCOPE_SERVER_ADDRESS
      value: "http://pyroscope:4040"
    - name: PYROSCOPE_APPLICATION_NAME
      value: "email.service"
    securityContext:
      capabilities:
        add:
        - SYS_PTRACE

Deploy the manifests:

kubectl apply -f https://raw.githubusercontent.com/infracloudio/microservices-demo-dev/master/release/kubernetes-manifests.yaml

Expose the Pyroscope service and access the UI: minikube service pyroscope Typical URL: http://192.168.49.2:30639

Pyroscope Resource Utilization

Pyroscope consumes very little CPU while storing data locally with BadgerDB, making it suitable for production environments.

Monitoring with Pyroscope

Pyroscope provides language‑specific flame graphs. Example screenshots (omitted) show profiling results for Go, Python, and .NET services.

Conclusion

Continuous profiling is essential for meeting user expectations. Pyroscope offers low‑overhead, language‑agnostic profiling that helps developers diagnose performance issues early, improve application speed, and lower cloud infrastructure costs.