Language Selection

English French German Italian Portuguese Spanish

Ubuntu 32-bit, 32-bit PAE, 64-bit Kernel Benchmarks

Filed under
Ubuntu

Coming up in our forums was a testing request to compare the performance of Linux between using 32-bit, 32-bit PAE, and 64-bit kernels. This is coming after Linus Torvalds has spoke of 25% performance differences between kernels using CONFIG_HIGHMEM4G and those without this option that allows 32-bit builds to address up to 4GB of physical RAM on a system. We decided to compare the performance of the 32-bit, 32-bit PAE, and 64-bit kernels on a modern desktop system and here are the results.

For this comparison we used Ubuntu 9.10 on a Lenovo ThinkPad T61 notebook running an Intel Core 2 Duo T9300 processor, 4GB of system memory, a 100GB Hitachi HTS7220 SATA HDD, and a NVIDIA Quadro NVS 140M. We were using the Ubuntu-supplied kernels that are based off the Linux 2.6.31 kernel in Ubuntu Karmic. Other packages that were maintained included GNOME 2.28.1, X Server 1.6.4, NVIDIA 195.22 display driver, GCC 4.4.1, and we were using the default EXT4 file-system with all other defaults. With Ubuntu to properly address 4GB or greater of system memory you need to use a PAE kernel as the Physical Address Extension support through the kernel's high-mem configuration options are not enabled in the default 32-bit kernels. CONFIG_HIGHMEM4G is enabled in the default Ubuntu kernel, but the Ubuntu PAE kernel uses CONFIG_HIGHMEM64G (and other build options) for handling up to 64GB of system memory. Of course, with 64-bit addressing there is not this greater than 4GB RAM limitation. Though even with a 32-bit non-PAE kernel the system will only report 3GB of system memory by default due to 1GB of that being reserved for kernel virtual addresses while the 3GB is available to user-space addresses.

rest here




More in Tux Machines

Running Linux On The Intel Compute Stick

The Intel Compute Stick has begun shipping, a tiny device that plugs into any HDMI TV or monitor and turns it into a fully-functioning computer. This low-power PC ships with Windows 8.1 or Ubuntu 14.04 LTS, though at the moment the Windows version is first to market with the Ubuntu Compute Stick not widely shipping until June. I have an Intel Compute Stick at Phoronix for testing. Read more

Research community looks to SDN to help distribute data from the Large Hadron Collider

There is one project called the LHC Open Network Environment (LHCONE) that was originally conceived to help with operations that involved multiple centers. To understand this, though, I have to explain the structure of the data and computing facilities. Read more

NASA Space App Challenger Runs Yocto on an Intel Edison-Based Nanosat

NASA has long had an interest in Linux and other open source technologies, and has used Linux in a variety of systems, including the R2 humanoid robot now at work at the International Space Station. With its International NASA Space App Challenge, the space agency is tapping into the maker gestalt to come up with new ideas, as well as inspire future space engineers. In this year's two-day Space App Challenge hackathon, which ran April 10-11 in 133 cities around the world, NASA greeted participants with over 25 challenges split into Earth, Outer Space, Humans, and Robotics categories. Read more

How to Find the Best Open Source Project to Work On

In my last article for Linux.com, I explored a few ways newcomers to open source projects can get started. While there are many resources to explore open source project communities, choosing which project to contribute to can still be a quite daunting task. You could go searching in the more than 23 million repositories on GitHub, the world’s largest source code hosting platform. But there are better ways. This article is meant to be a short guide to help novice open source practitioners more easily identify the first project they’d like to contribute to. Read more