Projects

perl-optimizer

Write your own Perl optimizer, in Perl. This module allows you to replace the default Perl optree optimizer, "peep", with custom Perl functions.

System Garden Habitat

Habitat from System Garden is a system monitor of applications and operating system, able to work stand alone or in groups and contribute to Harvest enterprise efficiency over the internet. A fast, graphical desktop tool lets you browse live data from the local client and other hosts that also ... [More] run Habitat. Data sets can come from local or peer Habitat colection agents, from Harvest repositories over the internet or from your own CSV files. It is able to pan and zoom into live or stored data sets to show data taken over years down to seconds, whilst maintaining an sensible time axis. [Less]

ATOP tool

Atop is an ASCII full-screen performance monitor that is capable of reporting the activity of all processes (even if processes have finished during the interval), daily logging of system and process activity for long-term analysis, highlighting overloaded system resources by using colors, etc. At ... [More] regular intervals, it shows system-level activity related to the CPU, memory, swap, disks, and network layers, and for every active process it shows the CPU utilization, the memory growth, priority, username, state, and exit code. [Less]

nuttcp

nuttcp is a network performance measurement tool intended for use by network and system managers. Its most basic usage is to determine the raw TCP (or UDP) network layer throughput by transferring memory buffers from a source system across an interconnecting network to a destination system, either ... [More] transferring data for a specified time interval, or alternatively transferring a specified number of bytes. In addition to reporting the achieved network throughput in Mbps, nuttcp also provides additional useful information related to the data transfer such as user, system, and wall-clock time, transmitter and receiver CPU utilization, and loss percentage (for UDP transfers). [Less]

Python Tracer

Lets you see your Python program's execution as a tree of function invocations, each tree node exposing the real time, and CPU time (user/sys) of that call. This project consists of two main components: A Python tracer that can run your Python programs (much like "cProfile" and ... [More] friends). A Gtk+ based GUI that can show the trace results. It uses a tiny auxiliary library written for it "graphfile" to allow append-only writing and reading static DAG's directly from file without reading it whole into memory at any stage. [Less]

newrelic_rpm

New Relic is a performance management system, developed by New Relic, Inc (http://www.newrelic.com). It provides you with deep information about the performance of your application as it runs in production. The New Relic Ruby Agent is dual-purposed as a either a Rails plugin or a Gem.

munin-varnish

varnish http proxy cache plugins for munin

aframework

A simple, modular ajax-ready php framework

database-analytics

The goal of this project is to develop a suitable database management system that is capable of efficiently handling heavy query processing and analytics. Rather than building an entire system from scratch, the project will be based on a stable existing open source database. The current target ... [More] is postgresql, mainly because it already provides many of the desired features. It will be retrofitted in a way that favors reads over transactions, however transaction processing still shouldn't be a major pitfall. The current objective is performance for operations that would otherwise run long times - to allow applications to perform more analysis and complex querying than with traditional databases; and, improve on the existing features of postgre. An additional feature is to provide for the ability to use the database for xml purposes, in a way that is transparent to the user; ie. they can use xquery and dump data as one would expect with a fully supported xml database. [Less]

dbperformanceanalysis

创建这个项目的时候原打算光对数据库进行性能分析和测试，但是因为考虑到学校实训的项目和自己在web方面的性能监控不仅在db方面，还扩大到了整个应用程序层次，而整个应用程序就非常复杂，光考虑数据库的性能远远不够� ... [More] �因此这个项目的测试对象扩大到整个应用程序层面 对web应用程序的性能分析时，不仅要考虑整个应用程序的性能，还要考虑各个层次的性能。 这些层次有：（假设php应用程序） php代码的性能 数据库的性能 服务器的性能 这是一个不同的web程序最需要关注的方面，在对其进行改进的时候，一定会加入其他一些层，比如对php代码进行优化的时候，你肯定会加入php代码缓存技术对编译完成的代码进行优化；对数据库进行优化的时候，你肯定会想到使用数据库缓存技术，在数据库和应用逻辑之间加入一个缓存服务器；在比如对服务器进行优化的时候，你肯定会想到负载均衡和缓存技术，这样会在原来的服务器和用户之间再加入一层用于控制负载等等等等。 但是上面那些层次是我认为最基本的，而且在本项目中，那些也是最基本的测试对象。 在开发测试程序的时候，遵循这样一个原则： 从大局出发，逐渐细化。先对整个应用程序进行测试，然后再测试各个层次 先对能快速提高整个应用程序性能的部分进行测试，然后再测试那些非主流的部分 先对容易测试的进行测试，然后是那些不太容易分析的部分。 服务器测试ab Siege PHP方面知识PHPOrPython (使用php还是使用python的思考) HowToUsePECL （如何使用PECL） HowToUsePEAR (如何使用PEAR) APD （advanced PHP debugger） PHPBenchmark (php语句的性能对比) 数据库Database 测试说明BenchMarking (压力测试说明) 其他的思考StudyOrProjects （我实在学习还是在做项目） [Less]