オンラインで Python コードパスのブロッキングスレッドを迅速に特定する方法（OpenResty XRay を使用）
- 問題: CPU 使用率が上がらない
- off-CPU 時間を最も占有する Python コードパスを特定
- 完全自動化された分析とレポート
- 問題: CPU 使用率が上がらない
- off-CPU 時間を最も占有する Python コードパスを特定
- 完全自動化された分析とレポート
OpenResty XRay を使用して Linux カーネルのトレースサブシステムにおける 2 つのバグを捕捉
- ユーザー空間メモリ読み取り時のカーネルデッドロック
- カーネル内の x86 ブレークポイント挿入におけるデータ競合
- ユーザー空間メモリ読み取り時のカーネルデッドロック
- カーネル内の x86 ブレークポイント挿入におけるデータ競合
Pinpointing hottest Perl code paths (using OpenResty XRay)
- Problem: high CPU usage
- Use the guidede analysis feature of OpenResty XRay to spot the hottest Perl code paths
- Automatic analysis and reports
- What is OpenResty XRay
- Problem: high CPU usage
- Use the guidede analysis feature of OpenResty XRay to spot the hottest Perl code paths
- Automatic analysis and reports
- What is OpenResty XRay
Pinpointing hottest Lua code paths in online OpenResty/Nginx servers (using OpenResty XRay)
- Problem: high CPU usage
- Use the guidede analysis feature of OpenResty XRay to spot the hottest Lua code paths
- Automatic analysis and reports
- Problem: high CPU usage
- Use the guidede analysis feature of OpenResty XRay to spot the hottest Lua code paths
- Automatic analysis and reports
How we solved a CPU bottleneck caused by Lua exceptions in a custom Kong plugin (using OpenResty XRay)
- The problem: high CPU usage in Kong servers
- The analysis & report
- The result: improved performance and reduced CPU usage
- The problem: high CPU usage in Kong servers
- The analysis & report
- The result: improved performance and reduced CPU usage
Memory and CPU usage statistics among Kong plugins online (using OpenResty XRay)
- CPU usage among all Kong plugins in a server process
- Memory usage among all Kong plugins in a server process
- Extra overhead for the servers
- CPU usage among all Kong plugins in a server process
- Memory usage among all Kong plugins in a server process
- Extra overhead for the servers
Troubleshooting the extra 200-ms request latency online
- The Problem
- The Analsysis Process
- Fully-automated analysis
- What is OpenResty XRay
- The Problem
- The Analsysis Process
- Fully-automated analysis
- What is OpenResty XRay
Pinpointing leaked Lua tables with OpenResty XRay's command-line tools
- How LuaJIT manages memory
- OpenResty XRay’s command-line tools
- An leaking example
- Analysis procedure
- lj-gco-ref analyzer
- Fully-automated analysis
- How LuaJIT manages memory
- OpenResty XRay’s command-line tools
- An leaking example
- Analysis procedure
- lj-gco-ref analyzer
- Fully-automated analysis
Real-Time Request Counting against Nginx Processes via YSQL
- How to install the run-ysql tool
- Count total requests served in real time
- Filter out specific requests
- Using YSQL in the Web Console
- True non-invasive tracing
- How to install the run-ysql tool
- Count total requests served in real time
- Filter out specific requests
- Using YSQL in the Web Console
- True non-invasive tracing
How to deploy the on-premises version of OpenResty XRay on Microsoft's Azure cloud
- Create a subscription and a resource group
- Create the Azure Kubernetes service
- Prepare the environment variables
- Log in to Azure from the command line
- Create the namespace and secret for Kubernetes
- Create the Azure Disk
- Update the configuration file for the persistent volume
- Update the Kubernetes configuration file
- Create the persistent volume
- Deploy the Kubernetes service
- Configure the application gateway
- Create a subscription and a resource group
- Create the Azure Kubernetes service
- Prepare the environment variables
- Log in to Azure from the command line
- Create the namespace and secret for Kubernetes
- Create the Azure Disk
- Update the configuration file for the persistent volume
- Update the Kubernetes configuration file
- Create the persistent volume
- Deploy the Kubernetes service
- Configure the application gateway
When Lua IPC Pipes Block OpenResty or Nginx's Event Loops
- The Problem
- Analyses
- Solutions
- Results
- The Problem
- Analyses
- Solutions
- Results
The Wonderland of Dynamic Tracing (Part 1 of 3)
- Dynamic Tracing
- What It Is
- Too Good to be True?
- How it Works
- Still Having Doubts?
- The Advantages of Dynamic Tracing
- DTrace
- SystemTap
- DTrace and SystemTap
- Applications of SystemTap in Production
- Dynamic Tracing
- What It Is
- Too Good to be True?
- How it Works
- Still Having Doubts?
- The Advantages of Dynamic Tracing
- DTrace
- SystemTap
- DTrace and SystemTap
- Applications of SystemTap in Production
The Wonderland of Dynamic Tracing (Part 2 of 3)
- Flame Graphs
- Methodology
- Knowledge Is Power
- Open-Source and Debug Symbols
- Flame Graphs
- Methodology
- Knowledge Is Power
- Open-Source and Debug Symbols
The Wonderland of Dynamic Tracing (Part 3 of 3)
- Dynamic Tracing Support in Linux Kernels
- Hardware Tracing
- Analyze Remains of Dead Process
- Traditional Debugging Technologies
- A Messy World of Debugging
- OpenResty XRay
- Dynamic Tracing Support in Linux Kernels
- Hardware Tracing
- Analyze Remains of Dead Process
- Traditional Debugging Technologies
- A Messy World of Debugging
- OpenResty XRay
Optimize Memory Fragmentation due to Huge Nginx Configuration
- Challenges
- Analyses
- Solutions
- Results
- Challenges
- Analyses
- Solutions
- Results
New FAQ Doc for OpenResty XRay
We recently prepared a new FAQ document for OpenResty XRay
We recently prepared a new FAQ document for OpenResty XRay
Automatic Analysis Reports in OpenResty XRay
- The Past
- The Present
- The Future
- The Past
- The Present
- The Future
Resolving Bilibili’s major site incident with OpenResty XRay
- The incident
- Process of resolution
- Hardening after the incident
- OpenResty XRay Services
- The incident
- Process of resolution
- Hardening after the incident
- OpenResty XRay Services
Tracing the Slowest PCRE Regular Expressions in OpenResty or Nginx Processes
- System Environment
- Narrowing Down the Culprit without Guessing
- Limiting the execution overhead of PCRE
- Non-Backtracking Regular Expression Engines
- Lua’s Builtin Patterns
- Tracing Applications inside Containers
- How The Tools are Implemented
- The Overhead of the Tools
- System Environment
- Narrowing Down the Culprit without Guessing
- Limiting the execution overhead of PCRE
- Non-Backtracking Regular Expression Engines
- Lua’s Builtin Patterns
- Tracing Applications inside Containers
- How The Tools are Implemented
- The Overhead of the Tools
Listing Loaded Lua Modules in OpenResty or Nginx Processes
- System Environment
- Names of Loaded Lua Modules
- Running Directly in the Web Console
- Tracing Applications inside Containers
- How The Tools are Implemented
- The Overhead of the Tools
- System Environment
- Names of Loaded Lua Modules
- Running Directly in the Web Console
- Tracing Applications inside Containers
- How The Tools are Implemented
- The Overhead of the Tools
