1. Computers
  2. Display Drivers
  3. Graphics Cards
  4. Memory
  5. Motherboards
  6. Processors
  7. Software
  8. Storage
  9. Operating Systems


Facebook RSS Twitter Twitter Google Plus


Phoronix Test Suite

OpenBenchmarking.org

Ubuntu 10.04 Already Shortens The Boot Time

Michael Larabel

Published on 18 December 2009
Written by Michael Larabel
Page 1 of 1 - 13 Comments

Ubuntu 10.04 Alpha 1 was released last week and while it did not bring any major features yet for this Long-Term Support release of Ubuntu Linux to be released in April of 2010, it began to introduce some underlying changes like the switch to the Linux 2.6.32 kernel, X Server 1.7, and the complete removal of HAL. Our early benchmarks of Ubuntu 10.04 show that there are some negative performance regressions right off the bat, but that is from within the Linux desktop. One area that Canonical is focusing upon in particular with Ubuntu 10.04 LTS is speeding up the boot process, so we decided to provide some benchmarks there too.

For Ubuntu 10.04 in fact they would like a 10 second boot time for Intel netbook hardware. Not only are they speeding up the boot process, but they are also working to beautify the boot process with Plymouth (video). For this article we checked out the boot performance with a Samsung NC10 that had an after-market OCZ SSD and 2GB of RAM along with a stock Dell Mini 9. Starting off, below are the Dell Mini 9 boot chart results for clean installations of Ubuntu 9.10 and then Ubuntu 10.04 Alpha 1.

The reported boot time for Ubuntu 9.10 on the Mini 9 was 59 seconds, but only 24 seconds in comparison for Ubuntu 10.04 Alpha 1. In the past, we had been able to boot Ubuntu 9.10 faster, but these are clean Bootchart results from Ubuntu 9.10 on a stock installation. The peak disk throughput was also higher under Ubuntu Lucid with a speed of 84MB/s compared to 79MB/s with Karmic. With Ubuntu 10.04 Alpha 1 there are less process starting up (such as with HAL being completely nuked) and the processes that are running are running faster. Also, we were measuring the boot chart results for each system and each Ubuntu release with an automated log-in to the GNOME desktop rather than the log-in screen. Below are the charts for the Samsung NC10.

For the Samsung NC10 the Karmic number was 55 seconds compared to 23 seconds with Lucid. The disk throughput for this OCZ Core Series V2 SSD was also noticeably better with Lucid at a peak of 122MB/s compared to 55MB/s with the stable Karmic.

Also surfacing this month is a new kernel (though it is currently based upon Linux 2.6.31 for Ubuntu 9.10) that pulls in more of Intel's Moblin speed patches from their kernel. As most know, Moblin 2 boots extremely fast. As is described on the mailing list, these kernel patches from Moblin remove a time delay in waiting for all devices before mounting the root file-system, KMS after SATA in drivers, don't blank the display, in the kernel DRM removing a root requirement for a DRM ioctl, fixing a vblank delay on pipe disable, make the device initialization go a-synchronously, and add an EDID cash for connected displays. We have tested out this kernel with the Moblin patches on Ubuntu 9.10 and it booted three seconds faster compared to the stock Karmic kernel.

As Ubuntu 10.04 matures, we will be back with more benchmarks. For now though you may be interested in the following articles: Measuring Ubuntu's Boot Performance, Measuring Fedora's Boot Performance, Checking In On Ubuntu Karmic's Boot Time, and ASUS Eee PC 901 Linux Boot Performance.

About The Author
Michael Larabel is the principal author of Phoronix.com and founded the web-site in 2004 with a focus on enriching the Linux hardware experience and being the largest web-site devoted to Linux hardware reviews, particularly for products relevant to Linux gamers and enthusiasts but also commonly reviewing servers/workstations and embedded Linux devices. Michael has written more than 10,000 articles covering the state of Linux hardware support, Linux performance, graphics hardware drivers, and other topics. Michael is also the lead developer of the Phoronix Test Suite, Phoromatic, and OpenBenchmarking.org automated testing software. He can be followed via and or contacted via .
Latest Articles & Reviews
  1. NVIDIA's $1000+ GeForce GTX TITAN X Delivers Maximum Linux Performance
  2. OS X 10.10 vs. Ubuntu 15.04 vs. Fedora 21 Tests: Linux Sweeps The Board
  3. The New Place Where Linux Code Is Constantly Being Benchmarked
  4. 18-GPU NVIDIA/AMD Linux Comparison Of BioShock: Infinite
  5. Phoronix Test Suite 5.6 Adds New Phoromatic Enterprise Benchmarking Features
  6. OpenGL Threaded Optimizations Responsible For NVIDIA's Faster Performance?
Latest Linux News
  1. Debian 8.0 Jessie RC2 Installer Released
  2. Shadow Warrior Is Being Released For Linux Next Week
  3. Intel Pushes A Bunch Of Broadwell Code Into Coreboot
  4. Open-Source Driver Fans Will Love NVIDIA's New OpenGL Demo
  5. GHC 7.10.1 Brings New Compiler Features
  6. Git 2.4.0-rc0 Does A Ton Of Polishing
  7. The Most Common, Annoying Issue When Benchmarking Ubuntu On Many Systems
  8. Mesa Is At Nearly 1,500 Commits This Year
  9. Gestures & Other GTK3 Features For LibreOffice
  10. It's Now Easier To Try PHP 7 On Fedora & RHEL
Most Viewed News This Week
  1. Introducing The Library Operating System For Linux
  2. AMD Is Hiring Two More Open-Source Linux GPU Driver Developers
  3. New SecureBoot Concerns Arise With Windows 10
  4. GNOME Shell & Mutter 3.16.0 Released
  5. GNU Nano 2.4.0 Brings Complete Undo System, Linter Support & More
  6. Systemd Change Allows For Stateless Systems With Tmpfs
  7. Red Hat Is Rolling Out A VirtIO DRM/KMS GPU Driver
  8. GCC 5 Compiler Is Getting Close To Being Released