Kindling
Overview and Concepts
Overview
Trace Profiling
RPC Trace
Roadmap
Prometheus vs. Kindling vs. APM
How Kindling Agent is going to evolve
Installation
Kindling Agent
Requirements
Install Kindling in Kubernetes
Setting up Grafana
FAQ
Download Linux kernel headers
Usage
How to enable Trace Profiling
Prometheus Metrics Description
Use Cases
Service Map and Performance
Observe Java Lock
Developer Guide
Architecture
Build Kindling container image from source codes
Kindling agent-libs 用户态空间数据流
Kindling agent-libs内核态空间数据流
Kindling collector 流水线数据传递流程
Add new eBPF hooks
Kindling probe核心流程
Developer FAQ
Reference
Kindling Java Agent
Overview
Modifications of async-profiler
async-profiler 改造点
Trace Profiling Operation Manual
本文档使用 MrDoc 发布
-
+
home page
Roadmap
## Goal The goal of Kindling is trying to help users understand the app behavior from kernel to user code stack. With the service map, network detail breakdown, and network-related metric, users can triage issues and route them to the corresponding team. With our trace-profiling, users can pinpoint the root cause in seconds. We have found that issues triage works well in the Kubernetes environment. If you find any issue that can't be identified which part(network, app code, infrastructure) causes the problem, please let us know. We will spend more time on triage work. As far as we know, even with tracing, metrics, and logging, users still can't pinpoint the root cause easily, so Kindling will spend more effort to help users find it with trace-profiling. The following work item list has been identified, and we will prioritize these work items based on the feedback of the community. If you want some work to be done first or have some suggestions for pinpointing root causes, please join our bi-weekly meeting or the WeChat group, and let us know your thoughts. ## Work Items ### Data Integration - Skywalking integration to get the trace info. (Done) - Opentelmentry integration to get the trace info. (TBD) - Pinpoint integration to get the trace info. (TBD) - Prometheus integration for detailed IO metrics, network metrics, and CPU metrics. (TBD) - Java code stack enhancement for network, file, and lock to help users understand how the userspace code causes the trace in waiting status. (TBD) - Java code flame graph and native code flame graph coexist (Currently only Java code flame graph has been used). (TBD) - Trace-profiling for Go/C/C++, currently trace-profiling only supports Java. (TBD) ### User-Friendly Enhancement - Trace-profiling sample strategy without intervention to keep those valuable profiling results. (TBD) ### More Features - Prometheus alert rule management. (TBD) - Python Anomaly Detection Toolkit (ADTK) be used for threshold in Prometheus alert rules(TBD) ### Others - Standard version of Kindling(TBD)
xieyun
Oct. 31, 2022, 4:57 p.m.
Share documents
Collection documents
Last
Next
Scan wechat
Copy link
Scan your mobile phone to share
Copy link
关于 MrDoc
觅思文档MrDoc
是
州的先生
开发并开源的在线文档系统,其适合作为个人和小型团队的云笔记、文档和知识库管理工具。
如果觅思文档给你或你的团队带来了帮助,欢迎对作者进行一些打赏捐助,这将有力支持作者持续投入精力更新和维护觅思文档,感谢你的捐助!
>>>捐助鸣谢列表
微信
支付宝
QQ
PayPal
Markdown文件
share
link
type
password
Update password