Catalogs >
Oracle >
Oracle Linux (White Paper)

Oracle Linux (White Paper)
23Pages

Add to favorites

Catalog excerpts

An Oracle White Paper Fast, Modern, Reliable: Oracle Linux

Open the catalog to page 1

Fast, Modern, Reliable: Oracle Linux

Open the catalog to page 2

Fast, Modern, Reliable: Oracle Linux Introduction to Oracle Linux Oracle Linux brings the latest Linux innovations to market, delivering extreme performance, advanced scalability, and reliability for enterprise applications. Oracle Linux offers two Linux kernels to choose from: • The Red Hat Compatible Kernel, for those who prefer strict Red Hat kernel ABI (kABI) compatibility or The Unbreakable Enterprise Kernel, for those who want to leverage the latest features from mainline Linux and boost performance and scalability. Oracle’s Unbreakable Enterprise Kernel is a fast, modern, reliable...

Open the catalog to page 3

Fast, Modern, Reliable: Oracle Linux Oracle VM Templates are pre-installed and pre-configured software images which eliminate installation and configuration costs, reduce ongoing maintenance costs, and help organizations achieve faster time to market and lower cost of operations. For more information on Oracle VM Templates, please visit this web page: http://www.oracle.com/technetwork/server-storage/vm/overview/templates-101937.html Extensively Tested and Certified Oracle invests significantly in testing and releasing critical bug fixes, making Oracle Linux an ideal option for enterprise...

Open the catalog to page 4

Fast, Modern, Reliable: Oracle Linux and many others, representing a wide range of server and storage product vendors, to make sure that a variety of fully integrated stacks are tested. Oracle and its strategic partners offer and recommend these configurations to enable end-users to deploy fully tested solutions to achieve standardization with high performance, scalability and reliability while lowering infrastructure costs and speeding up deployment. In general, many Unix OS vendors test their product in-house, focusing on testing the operating system specifically with the hardware and the...

Open the catalog to page 5

Fast, Modern, Reliable: Oracle Linux Oracle Linux with the Unbreakable Enterprise Kernel can be run directly on bare metal or as a virtual guest on Oracle VM or other virtualization technologies. The Unbreakable Enterprise Kernel version kernel-uek-2.6.32-100.34.1 added support for paravirtualized drivers in a HVM guest on Oracle VM. Starting with this kernel version, the default is to present only paravirtualized drivers when running in a hardware virtualized guest. To run kernel-uek – including the drivers – fully hardware virtualized, an additional kernel boot parameter...

Open the catalog to page 6

Fast, Modern, Reliable: Oracle Linux Oracle Achieves Record TPC-C Benchmark Result on 2 Processor System http://www.oracle.com/us/corporate/press/1853058 Oracle Delivers World Record x86 Performance on Industry Standard Java Middleware and Transactional Database Benchmarks http://www.oracle.com/us/corporate/press/1570421 Oracle Achieves World Record Two Processor Result with SPECjEnterprise2010 Benchmark http://www.oracle.com/us/corporate/press/1584316 Oracle Delivers World Record x86 Performance on Industry Standard Java Middleware and Transactional Database Benchmarks...

Open the catalog to page 7

Fast, Modern, Reliable: Oracle Linux Features and Performance Improvements Oracle Linux with the Unbreakable Enterprise Kernel includes many enhancements, including bug fixes to improve virtual memory performance, network and disk I/O performance as well as improvements for large NUMA (Non-Uniform Memory Access) systems. In addition to performance improvements for large systems, Oracle Linux contains many features that are relevant to Linux running in the data center. Integration of the DTrace Dynamic Tracing Framework DTrace is a comprehensive dynamic tracing framework that was initially...

Open the catalog to page 8

Fast, Modern, Reliable: Oracle Linux For more information on features, installing and configuring Linux Containers on Oracle Linux, please refer to Chapter 9: Linux Containers in the Oracle Linux Administrator's Solution Guide (http://docs.oracle.com/cd/E37670_01/E37355/html/ol_containers.html). Btrfs File System Btrfs (B-tree file system) is the “next generation file system” for Linux. Pronounced as “Butter FS” or “B-tree FS”, it is a GPL licensed file system first developed by Oracle’s Chris Mason in 2007. Today, its development is still coordinated by Chris Mason in collaboration with...

Open the catalog to page 9

Fast, Modern, Reliable: Oracle Linux core. This allows protocol processing (e.g. IP and TCP) to be performed on packets in parallel and avoids performance penalties that can occur due to the resulting cacheline bouncing. This solution removes a bottleneck where a single CPU core could be saturated from processing network interrupts. This feature has initially been back-ported into Unbreakable Enterprise Kernel Release 1 (2.6.32) from the mainline Linux 2.6.35 kernel, it is included by default in the second release of the Unbrekable Enterprise Kernel (2.6.39).To enable receive packet...

Open the catalog to page 10

Fast, Modern, Reliable: Oracle Linux A patch to list message signaled interrupts (MSI) for each device in the sysfs file system. Before, when MSI-X mode was enabled for a PCI device, there was no entry in sysfs that displayed the IRQs. The interrupts were only displayed in /proc/interrupts, but it was impossible to determine which interrupts were used by which device when there were multiple identical devices in the system. With the help of a modified irqbalance utility, this ensures to keep IRQs on NUMA local CPUs. Reduced runqueue lock contention by making improvements around IPC...

Open the catalog to page 11

Fast, Modern, Reliable: Oracle Linux Per-device buffered write accounting. The accounting for dirty pages has been reorganized, removing stalls and inefficient writeback when devices of different speeds are mixed together. Task Control Groups TCG can track and group processes into user-defined cgroups so that the operating system can treat them as whole and perform scheduling, accounting, and resource allocation accordingly. For example, using TCG, you can associate a set of CPU cores and memory nodes to a group of processes that makeup an application or a group of applications. This...

Open the catalog to page 12