Welcome!

Linux Containers Authors: Liz McMillan, Yeshim Deniz, Elizabeth White, Pat Romanski, Zakia Bouachraoui

Related Topics: Linux Containers

Linux Containers: Article

Introducing the Linux 2.6 Kernel

Introducing the Linux 2.6 Kernel

Already the subject of intense scrutiny, this new kernel will be the first major revamp of the Linux kernel in two years. We at Open Source Development Labs (OSDL) have worked with Linux developers and together completed more than 4,000 tests on publicly available development versions of this kernel.

In recent months, we have run the development kernel, known as 2.5, in our production environment with servers, achieving more than 30 days of continuous uptime. The 2.5 kernel will transition into 2.6, and OSDL is committed to its rapid adoption in the market. (OSDL is a global consortium backed by Computer Associates, Fujitsu, Hitachi, HP, IBM, Intel, NEC, and other major vendors.)

A fast and deep entry into the market would be a distinct change from what happened with Linux 2.4, when adoption took longer than the industry anticipated. This time around, however, the development community, including OSDL, has tested the kernel so extensively that we believe adoption will come much, much faster.

There are eight reasons why CIOs will decide to upgrade to a Linux distribution based on 2.6: seven related to performance and the eighth, and critical, factor being cost. At OSDL, we divided the key 2.6 kernel feature improvements into seven categories: performance, scalability, availability, clustering, I/O, management, and serviceability. We found that Linux systems based on the 2.6 kernel will scale better on bigger machines. This provides the opportunity to replace more proprietary Unix servers and to consolidate workloads on bigger Linux systems. But it's not just the technical features; the clincher is the cost savings that these features will make possible for large organizations.

Businesses can save big money by implementing the new Linux kernel on Intel architecture-based servers. Amazon's move from Solaris to Linux on HP NetServer systems helped Amazon slash its technology capital budget more than 25% in the first year alone. There's more: businesses can achieve lower training costs, and additional savings can be found as Unix technical staff can easily port their skills, procedures, and even many applications to Linux.

To borrow an insight from Clayton Christensen's book, The Innovator's Dilemma (HarperBusiness, 2000), Linux is a disruptive technology. The new kernel is going to allow Linux to pass Christensen's "good enough" test. This means that many organizations are going to begin moving their core data center operations over to Linux. It gets the job done for a lot less money. As proprietary architectures yield their performance advantage to Linux, Linux becomes "good enough" for most workloads.

Scalability
"Does Linux scale?" is often the first question an IT manager will ask when evaluating whether Linux can replace an enterprise Unix server. Our tests indicate that the Linux 2.6 kernel will scale much better than the 2.4 kernel. Most of the development of the 2.4 kernel was done on single-processor systems with some testing on dual-processor and larger systems. The larger 8- and 16-way machines are supported, but the 2.4 kernel isn't really aimed at those system sizes. With the 2.6 kernel, performance is dramatically improved on large machines.

As part of OSDL's charter we provide outside developers access to enterprise-class machines. Testing on multiprocessor machines is a vital part of the Linux development process and has resulted in an improved scheduler, kernel native threading, and overall refinement of the locking granularity.

We also did a lot of testing of these larger machines with databases, which are a classic resource-intensive, business-critical workload. OSDL provided the Database Test Suite, a fair-use implementation of Transaction Processing Performance Council (TPC) benchmarks. These database performance test results comparing the Linux 2.4 kernel to the Linux 2.5 kernel are freely available from OSDL at www.osdl.org/projects/performance. The source code for the tests is also available for developers.

Stability
"Is Linux stable on larger systems?" is probably the second most frequently asked question. OSDL put a lot of time and resources into testing the Linux 2.5 kernel through the Linux Stabilization Project. A description of the tests and results is available at www.osdl.org/projects/26lnxstblztn/results. Based on these tests and our experience with the 2.5 kernel, we expect that the Linux 2.6 kernel will be more stable than the Linux 2.4 kernel was when it was released.

There is a companion project to test scalability in a repeatable scientific environment. OSDL's Scalable Test Platform (STP) and Patch Lifecycle Manager (PLM) provide the Linux development community with an open, easy-to-use resource for testing custom kernels. STP works as the testing engine. PLM makes it easy to manage developers' patches against stock kernels. With a consistent set of hardware and test suites, developers can test new features in a controlled environment.

Planning for the Future
Because of the improvements in scalability, stability, performance, and availability in the kernel, Linux has reached the level where it can replace more expensive Unix servers. IT managers need to evaluate Linux suitability for their data centers based on the features it will have at the time of deployment. The rapid development of Linux adds some challenges to plans to adopt it. IT managers need to become familiar with the improvements to the 2.6 kernel, determine suitability for their enterprise, and insist on these features when preparing Request for Proposals (RFPs) or making a purchase.

The Linux 2.6 kernel will support more hardware platforms, bringing businesses savings in reduced management costs through a reduction in the number of operating systems under management. Instead of a variety of Unix versions, businesses can standardize on Linux on a range of hardware architectures. Most of Linux runs on industry-standard Intel architecture servers, available from almost every vendor, including Dell, HP, IBM, and NEC. Linux also runs on mainframes from IBM and Fujitsu, PowerPC-based servers from IBM, and Itanium-based servers from HP.

When IT managers plan for the future, they should keep in mind that Linux server use is growing and Unix server use is shrinking. According to industry research firm Gartner, hardware vendors shipped over 425,000 servers with Linux last year, up from 286,823 in 2001. During the same time period, shipments of Unix machines fell 9%. Due to technical improvements in the 2.6 kernel, we anticipate that this trend will accelerate. Many more companies will follow Amazon's early lead and realize significant cost savings by migrating from Unix to Intel architecture hardware.

With the release of the new kernel, OSDL is refocusing much of its work on end-user Global 2000 corporations. We're interested in learning more about your plans to use Linux. What challenges remain before you are prepared for production deployment? With classic disruptive technologies, much like the original personal computer, we know that adoption of "good enough" technology accelerates in new and surprising ways. Tell us what your plans are for Linux. We invite your organization to participate with OSDL in making Linux ready for your enterprise.

For More Information
Learn more by visiting www.osdl.org, the OSDL site. Here you'll find information on Carrier Grade Linux, Data Center Linux, OSDL Database Test Suite, Linux Stabilization Project, Scalability Test Platform, Patch Lifecycle Manager, and much more.

What Is the Kernel?
The Linux kernel is the core of a Linux system. It is only a small part of the large number of files that are installed on a server's hardware. Programs like Web servers, databases, application servers, mail servers, compilers, text editors, image editors, and word processors are not part of the Linux kernel. The kernel controls access to system resources such as

  • CPU
  • RAM
  • Monitor, keyboard, mouse
  • Disk drives, CD-ROM drives
  • Tape drives, printers, and other peripherals and ports
  • Network access

There are two types of Linux kernels, development and production (or stable). Development kernels end in an odd number (e.g., 2.3 or 2.5). Production kernels end in even numbers (e.g., 2.4 or 2.6).

This numbering scheme divides Linux users into two categories. The first category consists of developers and testers, who use the odd-numbered kernels, which are changing and may be unstable. The second category consists of production users, who use even-numbered kernels, which change as little as possible.

Although there will be some settling of the fine points of kernel feature implementation and a deferral of features that aren't ready for production, a look at the 2.5 kernel will give a fairly good view of what the 2.6 kernel will become.

More Stories By Dave Fuller

Dave Fuller brings more than 25 years of data center technical and marketing experience to his current position leading the technical marketing group at OSDL, where he participates in both the Linux kernel stabilization project and the Data Center Linux working group. Prior to OSDL, Dave led IT activities at a start-up focused on Web commerce. At Sequent Computer Systems, he played key roles in technical services and oversaw technical sales support for the company's Asia-Pacific and Latin American operations.

Comments (1) View Comments

Share your thoughts on this story.

Add your comment
You must be signed in to add a comment. Sign-in | Register

In accordance with our Comment Policy, we encourage comments that are on topic, relevant and to-the-point. We will remove comments that include profanity, personal attacks, racial slurs, threats of violence, or other inappropriate material that violates our Terms and Conditions, and will block users who make repeated violations. We ask all readers to expect diversity of opinion and to treat one another with dignity and respect.


Most Recent Comments
Marky Goldstein 10/01/03 04:51:14 AM EDT

The Linux kernel should be improved for realtime audio- & video processing and clustering... ! That's home entertainment in the future...

IoT & Smart Cities Stories
The deluge of IoT sensor data collected from connected devices and the powerful AI required to make that data actionable are giving rise to a hybrid ecosystem in which cloud, on-prem and edge processes become interweaved. Attendees will learn how emerging composable infrastructure solutions deliver the adaptive architecture needed to manage this new data reality. Machine learning algorithms can better anticipate data storms and automate resources to support surges, including fully scalable GPU-c...
Machine learning has taken residence at our cities' cores and now we can finally have "smart cities." Cities are a collection of buildings made to provide the structure and safety necessary for people to function, create and survive. Buildings are a pool of ever-changing performance data from large automated systems such as heating and cooling to the people that live and work within them. Through machine learning, buildings can optimize performance, reduce costs, and improve occupant comfort by ...
The explosion of new web/cloud/IoT-based applications and the data they generate are transforming our world right before our eyes. In this rush to adopt these new technologies, organizations are often ignoring fundamental questions concerning who owns the data and failing to ask for permission to conduct invasive surveillance of their customers. Organizations that are not transparent about how their systems gather data telemetry without offering shared data ownership risk product rejection, regu...
René Bostic is the Technical VP of the IBM Cloud Unit in North America. Enjoying her career with IBM during the modern millennial technological era, she is an expert in cloud computing, DevOps and emerging cloud technologies such as Blockchain. Her strengths and core competencies include a proven record of accomplishments in consensus building at all levels to assess, plan, and implement enterprise and cloud computing solutions. René is a member of the Society of Women Engineers (SWE) and a m...
Poor data quality and analytics drive down business value. In fact, Gartner estimated that the average financial impact of poor data quality on organizations is $9.7 million per year. But bad data is much more than a cost center. By eroding trust in information, analytics and the business decisions based on these, it is a serious impediment to digital transformation.
Digital Transformation: Preparing Cloud & IoT Security for the Age of Artificial Intelligence. As automation and artificial intelligence (AI) power solution development and delivery, many businesses need to build backend cloud capabilities. Well-poised organizations, marketing smart devices with AI and BlockChain capabilities prepare to refine compliance and regulatory capabilities in 2018. Volumes of health, financial, technical and privacy data, along with tightening compliance requirements by...
Predicting the future has never been more challenging - not because of the lack of data but because of the flood of ungoverned and risk laden information. Microsoft states that 2.5 exabytes of data are created every day. Expectations and reliance on data are being pushed to the limits, as demands around hybrid options continue to grow.
Digital Transformation and Disruption, Amazon Style - What You Can Learn. Chris Kocher is a co-founder of Grey Heron, a management and strategic marketing consulting firm. He has 25+ years in both strategic and hands-on operating experience helping executives and investors build revenues and shareholder value. He has consulted with over 130 companies on innovating with new business models, product strategies and monetization. Chris has held management positions at HP and Symantec in addition to ...
Enterprises have taken advantage of IoT to achieve important revenue and cost advantages. What is less apparent is how incumbent enterprises operating at scale have, following success with IoT, built analytic, operations management and software development capabilities - ranging from autonomous vehicles to manageable robotics installations. They have embraced these capabilities as if they were Silicon Valley startups.
As IoT continues to increase momentum, so does the associated risk. Secure Device Lifecycle Management (DLM) is ranked as one of the most important technology areas of IoT. Driving this trend is the realization that secure support for IoT devices provides companies the ability to deliver high-quality, reliable, secure offerings faster, create new revenue streams, and reduce support costs, all while building a competitive advantage in their markets. In this session, we will use customer use cases...