libnodelay is an LD_PRELOAD library for disabling Nagle's algorithm. Disabling Nagle's algorithm can result in a performance improvement for latency-sensitive applications that use TCP. Using the library may be easier than digging through a mess of code and confusing or obscure configuration options.
PerfMonger is an yet another performance monitoring tool. The monitoring targets of PerfMonger are similar to the ones of sysstat (CPU usages, IO usages, etc.), but PerfMonger can collect and report performance information very frequently (the reporting interval of sysstat is 1 second at minimum, but PerfMonger can use a much smaller interval such as 0.5 seconds or 0.01 seconds) and can display performance information in both human-readable and machine-readable formats.
BlackRay is a relational database system designed to offer performance features commonly associated with search engines. It offers SQL support and sophisticated operational and management features. Load-balancing and operational stability by means of N+1 redundance are included. BlackRay is called a "Data Engine" since it combines traditional, relational database features and SQL with the power and flexibility of search engines. It is a true hybrid, offering transaction support, data-versioned snapshots, and sophisticated function-based indices. Wildcards, phonetic, and fuzzy logic searches are supported, as well. BlackRay supports a subset of the SQL92 standard and provides JDBC/ODBC/native driver options via the PostgreSQL protocol, in addition to an API based query option. The project is released under the GPLv2, with some drivers available under BSD-style licenses. Commercial support contracts are available as well.
Torrus is an alternative software platform to MRTG, Cricket, and Cacti. In most cases it brings more flexibility and performance. It is able to poll more than 50,000 SNMP OIDs every 5 minutes from a single moderately equipped server, with simultaneous threshold monitoring of half of them. Torrus is designed to be a universal data series processing framework. Its scalable hierarchical design, application-independent core, and highly customizable architecture make it an attractive choice both for small installations and for big enterprise or carrier networks. Although most users deploy Torrus for SNMP monitoring, it might be useful for data series of any nature. Tobi Oetiker's RRDtool is used for data storage.
RegressionSuite is a software test suite that incorporates measurements of startup lag and accurate execution times, generating execution statistics, customized input distributions, and processable regression specific details as part of the regular unit tests. It provides a framework around which the individual unit regressors are invoked (and details and statistics collected). Unit regressors are grouped into named regressor sets (or modules), and regressors are created by implementing specific regressor interfaces. These two features make regressors particularly amenable to testing analytics (and other similarly state-light) modules.
gprog is a basic GUI pipe meter that shows the percentage complete as data moves through a Unix pipe. It is very fast because it uses a dual process design with a cache oblivious algorithm for self-tuning. Also, the presentation is largely decoupled from the transfer, so that the GUI won't slow down the transfer.
Pylot is a tool for testing the performance and scalability of Web services. It runs HTTP load tests, which are useful for capacity planning, benchmarking, analysis, and system tuning. It generates concurrent loads, verifies server responses, and produces reports with metrics. Tests suites are executed and monitored from a GUI or the shell.
Immutables allows you to embrace immutablity to tackle complexity and concurrency challenges. To get the benefits of immutability in Java, there's an annotation processor to easily create simple and consistent value objects. You can think of it as Guava's Immutable Collections but for regular objects. It includes support for JSON marshaling, MongoDB repositories, and JAX-RS.
Data Shovel Pinnacle Performance Utilities is a collection of utilities for large input/output tasks. bare takes line feed-separated file names on standard input and concatenates the file contents on standard output. baresha512 takes line feed-separated file names on standard input and provides the SHA512 message digest for the concatenated file content on standard output. Both can optionally open and read files with O_DIRECT, bypassing the kernel's block cache. cock provides a digital petcock. It relives I/O pressure on the kernel by rate limiting data throughput. It can auto-throttle to mitigate lag spikes, or use a specified megabytes-per-second rate limit.