Boost Kubernetes Microservice Performance with Pyroscope Continuous Profiling

Developers often need to locate performance bottlenecks in production applications, but traditional log‑based methods are time‑consuming and lack detail. A modern approach is continuous profiling, which highlights the slowest code paths that consume the most resources.

What Is Pyroscope?

Pyroscope is an open‑source continuous profiling platform composed of a server and agents. It collects, stores, and queries profiling data efficiently, allowing developers to diagnose performance issues, reduce CPU/memory consumption, and improve user experience.

Profiling measures memory usage, time complexity, and function call frequency/duration, providing data for optimization. A continuous profiler runs in production, continuously gathering code‑level performance data.

Available Continuous Profilers

Pyroscope

Parca

Datadog Continuous Profiler

Google Cloud Profiler

Pyroscope distinguishes itself by offering a purpose‑built storage engine and supporting language‑specific agents for Go, Python, Ruby, eBPF, Java, .NET, PHP, and Rust.

Why Use Pyroscope?

Compared with Datadog and Google Cloud Profiler, Pyroscope provides a low‑overhead, high‑efficiency storage engine (Badger) and supports both language‑specific and eBPF agents, delivering more readable profiles.

Installing Pyroscope on Kubernetes

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 installation, the Pyroscope UI is reachable via the service URL provided by minikube service pyroscope.

Integrating Pyroscope with Google Microservices Demo

Modify each service’s Dockerfile to include the Pyroscope binary and start the application through it.

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"]

Go Service

import (
    pyroscope "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
}

Build and push the Go image similarly.

Updating Kubernetes Manifests

Add the Pyroscope sidecar image and environment variables to each container, and grant the SYS_PTRACE capability.

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

Deploy the updated manifests:

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

Access the Pyroscope UI (e.g., http://192.168.49.2:30639) to view flame graphs and resource usage.

Resource Utilization

Pyroscope runs with minimal CPU overhead and stores data locally using Badger, making it cost‑effective for production environments.

Monitoring with Pyroscope

Flame graphs for different languages (Go, Python, .NET, etc.) illustrate hot paths and help pinpoint inefficient code.