Orbit

Orbit 是一套用于 C 和 C++ 性能分析、二进制符号映射以及远程进程和线程分析的专门工具。它提供了一个用于分析执行时间和资源使用情况的系统，利用调用图可视化器将函数进入和退出映射到单个线程的分层执行流中。

该项目的特色在于一个远程进程分析器，能够从在远程主机上运行的应用程序中捕获性能数据。它还包括一个线程调度分析器，用于跟踪上下文切换和处理器核心利用率，以可视化线程行为。

总的来说，该工具集涵盖了应用程序性能采样和执行流可视化。它通过构建 ID 加载外部符号文件来支持调试，并提供会话管理以持久化检测 Hook 和符号元数据。

Features

C Performance Profiling - Provides comprehensive performance profiling for C and C++ applications to identify bottlenecks and resource usage.
Debug Symbol Loaders - Loads debug symbols from external files using build IDs for on-demand binary-to-source lookup.
Call Graph Visualizations - A feature in the tool that tracks function entries, exits, and scheduling events to create per-thread hierarchical call graphs.
Symbol-To-Address Mapping - Provides a mechanism to map binary addresses back to source code identifiers using build identifiers.
Call Graph Visualizers - Generates hierarchical representations of function entries and exits to visualize execution flow for threads.
Remote Debugging - Captures performance data from applications running on remote hosts to analyze behavior in production.
Context-Switch Analysis - Tracks context switches and processor core utilization to identify bottlenecks in multi-threaded execution.
CPU Scheduling Event Recorders - Records kernel scheduling events to visualize thread migration and execution gaps across CPU cores.
Asynchronous Thread Schedulers - Records and visualizes the coordination of threads across multiple processor cores via context-switch tracking.
Data Collection Agents - Deploys agents on remote hosts to capture execution metrics and transmit them for analysis.
Remote Profiling Interfaces - Provides interfaces to trigger and retrieve performance profiles from applications running on remote hosts.
Thread Performance Analyzers - Analyzes CPU-intensive threads by tracking context switches and processor core utilization.
Application Performance Profiling - Identifies high-overhead functions through sampling to determine areas requiring detailed instrumentation.
Instruction Sampling - Implements sampling-based performance measurement to estimate function overhead by capturing the instruction pointer.

Star 历史

googleorbitArchived

Name: google/orbit
Author: google

View on GitHub

4,316 星标358 分支C++BSD-2-Clause5 次浏览orbitprofiler.com

Orbit

Features

C Performance Profiling - Provides comprehensive performance profiling for C and C++ applications to identify bottlenecks and resource usage.
Debug Symbol Loaders - Loads debug symbols from external files using build IDs for on-demand binary-to-source lookup.
Call Graph Visualizations - A feature in the tool that tracks function entries, exits, and scheduling events to create per-thread hierarchical call graphs.
Symbol-To-Address Mapping - Provides a mechanism to map binary addresses back to source code identifiers using build identifiers.
Call Graph Visualizers - Generates hierarchical representations of function entries and exits to visualize execution flow for threads.
Remote Debugging - Captures performance data from applications running on remote hosts to analyze behavior in production.
Context-Switch Analysis - Tracks context switches and processor core utilization to identify bottlenecks in multi-threaded execution.
CPU Scheduling Event Recorders - Records kernel scheduling events to visualize thread migration and execution gaps across CPU cores.
Asynchronous Thread Schedulers - Records and visualizes the coordination of threads across multiple processor cores via context-switch tracking.
Data Collection Agents - Deploys agents on remote hosts to capture execution metrics and transmit them for analysis.
Remote Profiling Interfaces - Provides interfaces to trigger and retrieve performance profiles from applications running on remote hosts.
Thread Performance Analyzers - Analyzes CPU-intensive threads by tracking context switches and processor core utilization.
Application Performance Profiling - Identifies high-overhead functions through sampling to determine areas requiring detailed instrumentation.
Instruction Sampling - Implements sampling-based performance measurement to estimate function overhead by capturing the instruction pointer.

Orbit 的开源替代方案

相似的开源项目，按与 Orbit 的功能重合度排序。

jrfonseca/gprof2dot
jrfonseca/gprof2dot
3,434在 GitHub 上查看
gprof2dot is a performance graph generator and visualizer that converts gprof GNU profiler execution profiles into Graphviz DOT files. It transforms raw profiler data into a directed graph to map function call hierarchies and identify software bottlenecks. The tool employs heuristic-based color mapping to highlight performance hotspots by assigning colors to nodes and edges based on execution time percentages. It also supports differential profile analysis, allowing for the comparison of two distinct execution graphs to identify changes in timing and call counts between runs. To improve visu
Pythonc-plus-plusgraphprofiling
在 GitHub 上查看3,434
wolfpld/tracy
wolfpld/tracy
15,298在 GitHub 上查看
Tracy is a real-time performance profiling framework for C and C++ applications. It provides a software instrumentation library that captures high-resolution telemetry data, which is then visualized through a separate graphical interface to identify bottlenecks and resource allocation issues. The system utilizes a client-server architecture that enables remote profiling, allowing performance data to be captured on a target machine and analyzed on a workstation. It employs lock-free event logging and shared-memory ring buffers to minimize the overhead of data collection, ensuring that the main
C++gamedevgamedev-librarygamedevelopment
在 GitHub 上查看15,298
uber-archive/go-torch
uber-archive/go-torch
3,941在 GitHub 上查看
go-torch is a profiling tool for capturing the execution state of Go programs and transforming raw binary data into visual representations of program performance. It functions as a flame graph profiler and performance visualization utility that identifies expensive code paths through the collection of CPU and memory stack traces. The tool features a network-capable remote process profiler that connects to endpoints to capture and export execution profiles from Go binaries. It utilizes stochastic profiling to synthesize execution data into call graphs, allowing for the identification of bottle
Go
在 GitHub 上查看3,941
racket/racket
racket/racket
5,157在 GitHub 上查看
Racket is a general-purpose, multi-paradigm programming language in the Lisp family designed for language creation. It functions as a language workbench, providing a platform for designing and implementing custom programming languages through a flexible system of macros and modules. The system distinguishes itself by offering a comprehensive suite for semantics engineering, allowing for the construction of specialized language subsets and educational layers. It includes tools for custom language design, such as lexer and parser generation, as well as the ability to define module expansion rul
Racketracket
在 GitHub 上查看5,157

查看 Orbit 的所有 30 个替代方案

常见问题解答

google/orbit 是做什么的？

google/orbit 的主要功能有哪些？

google/orbit 的主要功能包括：C Performance Profiling, Debug Symbol Loaders, Call Graph Visualizations, Symbol-To-Address Mapping, Call Graph Visualizers, Remote Debugging, Context-Switch Analysis, CPU Scheduling Event Recorders。

google/orbit 有哪些开源替代品？

google/orbit 的开源替代品包括： jrfonseca/gprof2dot — gprof2dot is a performance graph generator and visualizer that converts gprof GNU profiler execution profiles into… wolfpld/tracy — Tracy is a real-time performance profiling framework for C and C++ applications. It provides a software… uber-archive/go-torch — go-torch is a profiling tool for capturing the execution state of Go programs and transforming raw binary data into… racket/racket — Racket is a general-purpose, multi-paradigm programming language in the Lisp family designed for language creation. It… joerick/pyinstrument — pyinstrument is a statistical sampling profiler for Python that records the call stack at regular intervals to… miniprofiler/rack-mini-profiler — This project is a performance analysis tool for Ruby applications using the Rack interface. It monitors request…