Java ProfilerLow-overhead Java profiling for Kubernetes incidents

Find the Java stack behind a Kubernetes performance problem with opt-in profiling, real async-profiler/JFR evidence, and a focused diagnosis UI.

Opt in when you need it

Enable profiling with Kubernetes metadata. The node-local collector keeps collection controlled and retention at seven days or less.

CPU, Wall Clock, I/O wait, GC, allocation, lock, thread, deadlock, status, and ingestion data stay tied to one service and time range.

async-profiler data lands in ClickHouse and the project UI; Pyroscope, Parca, and Grafana are not required backend dependencies.

Check target status, then use CPU or allocation. Move to Wall Clock, I/O, GC, locks, or ingestion when the first view does not explain the incident.

Real allocation profile analysis from the acceptance environment

Open Quickstart and enable profiling with Kubernetes metadata.
Open the target service and check status to confirm that the JVM was accepted.
Start with cpu or memory, then move to wall, io, gc, locks, or ingestion as the incident requires.

Quickstart: enable profiling and read your first service profile.
Performance Analysis Manual: read CPU, Wall Clock, Java I/O wait, GC, allocation summary, lock, deadlock, target status, profile evidence guidance, and ingestion evidence.
Java Profiling Runbook: enable temporary or continuous profiling for a Kubernetes workload.

Deployment and Operations: install, secure, operate, upgrade, and troubleshoot the profiler.
Real Profiling Acceptance: prove CPU, Wall Clock, Java I/O wait, GC, allocation, lock, ClickHouse, UI, and ingestion behavior before shipping changes.

Contributing: run local checks, build docs, and execute real acceptance.
Architecture: understand the collector, backend, ClickHouse store, contracts, and web UI.
E2E Automation Guide: run browser and real Kubernetes acceptance flows.
Profiling Contracts: inspect stable payload and configuration contracts.
GitHub Issues: report bugs and request changes.

Use the English / 简体中文 switch in the top bar to change languages.
The screenshots on this page come from a real acceptance environment. The allocation screenshot shows the current Allocation Summary and flamegraph workflow; it is not mocked UI state.

Run these commands from the repository root:

bash

cd docs
npm install
npm run docs:dev

Build the publishable static site:

bash

cd docs
npm run docs:build