Since Friday there's been a number of Phoronix articles about a very bad power regression in the mainline Linux kernel, which is widespread, Ubuntu 11.04 is one of the affected distributions, and has been deemed a bug of high importance. This yet-to-be-resolved issue is affected Linux 2.6.38 and 2.6.39 kernels and for many desktop and notebook systems is causing a 10~30% increase in power consumption. Nevertheless, this is not the only major outstanding power regression in the mainline tree, there is another dramatic regression now spotted as well that is yet-to-be-fixed.
Ubuntu 11.04 "Natty Narwhal" is set to be released on Thursday and while there are a number of new features to talk about in this latest release, the Phoronix Test Suite software has been busy analyzing the performance of this latest release. There is open-source graphics driver improvements leading to some performance improvements (such as Radeon KMS page-flipping), the famous ~200 line Linux kernel patch to improve responsiveness, and various other enhancements that catch our fancy in Ubuntu 11.04. However, one area where there is a frightening regression in Ubuntu 11.04 is with its power consumption. For mobile devices in many workloads, Ubuntu 11.04 is consuming noticeably more power than in any of the past Ubuntu Linux releases. Sadly, no one seems to have noticed in time since continuous integration testing on Linux seems to happen so haphazardly right now.
For those that follow my personal Twitter feed will know that for the past week I've been closely testing Ubuntu 11.04 and all Ubuntu releases going back to Ubuntu 8.04 on many mobile devices in the office. The overall system performance, power consumption, and boot performance have been the principal targets. However, late this week I discovered a glaring regression: Ubuntu 11.04 is viciously going through power. Compared to Ubuntu 10.10, the power consumption on Ubuntu 11.04 for mobile devices is up about 10% on average but under some workloads, I am seeing the power consumption up by nearly 30%. This is happening on many mobile systems spanning multiple generations of Intel CPUs and with Intel / ATI / NVIDIA graphics. This issue has been tracked down to a frightening kernel regression in the mainline tree that is still not addressed.
Upon the release of the first Mac OS X 10.7 "Lion" Developer Preview, we had delivered early benchmarks of this Apple operating system slated for release this summer. Since then, there has been the release of Mac OS X 10.7 Developer Preview 2 (DP2) so we have carried out an updated set of Mac OS X 10.7 performance benchmarks. This also includes a comparative look at the Mac OS X Lion performance against Ubuntu Linux 10.10.
At the end of 2009 I published benchmarks comparing Ubuntu's 32-bit, 32-bit PAE, and 64-bit Linux kernels. Those tests were carried out to show the performance impact of using 32-bit with PAE (Physical Address Extension) support, which on the plus side allows up to 64GB of system memory to be addressable from 32-bit machines, but is still significantly slower than a 64-bit kernel and user-space. In this article the tests have been carried out on modern hardware and with the latest Ubuntu 11.04 packages to see how the three kernel variants are performing in 2011.
By now you have likely read all about the features announced for Mac OS X 10.7 "Lion" thus far along with seeing plenty of screenshots and videos showing off Launchpad, Mission Control, Versions, the improved mail client, and much more. But how does Apple's next-generation operating system perform? Well, here is a look at the performance of Mac OS X 10.7, including what are likely the first public benchmarks of Mac OS X Lion.
In this article we are looking at how Linux, OpenSolaris, and FreeBSD scale across multiple cores. Benchmarked are CentOS 5.5, Fedora 14, PC-BSD/FreeBSD 8.1, and OpenIndiana b148 as we see how the performance differs when running on one, two, three, four, and six cores, plus when Intel Hyper Threading is enabled.
In recent weeks we have been talking about Intel's Linux advancements as it concerns their latest "Sandy Bridge" generation of processors with integrated graphics (and there are a few more articles on the way), but how is their latest open-source driver stack performing on the older generations of Intel integrated graphics? Previously, the Intel Linux graphics have been the real loser in our multi-OS comparisons, but is this still the case? At least when comparing the Linux and Mac OS X performance on Intel 945 hardware, yes, the Mesa driver falls behind at OpenGL acceleration.
Earlier this week on Phoronix were new benchmarks of Ubuntu Linux vs. Mac OS X using a new Apple Mac Book Pro with an Intel Core i5 CPU and a NVIDIA GeForce GT 330M graphics processor. When looking at the tests results overall it ended up being a competitive race between these two Microsoft Windows competitors. In some areas, like the OpenCL computational performance, Apple's operating system commanded a sizable lead. In other areas, like the OpenGL graphics performance, Ubuntu Linux backed by NVIDIA's official but proprietary driver was in control. Here's an additional set of tests showing the measurable leads of NVIDIA Linux over Mac OS X with Apple's NVIDIA driver.
Back in May, we published benchmarks of Mac OS X 10.6.3 vs. Windows 7 vs. Ubuntu 10.04, along with other times, looking at the performance of Apple's Mac OS X operating system relative to Ubuntu and other Linux distributions. In most of those articles though we used Mac Mini computers, but now with a new Mac Book Pro in our labs with the latest Apple/Intel hardware, along with the most recent versions of each operating system, we have carried out a new set of tests that is also more in-depth than our earlier published benchmarks.
Ubuntu 11.04 Alpha 1 is set to be released today and many of you have been wondering what Canonical's Unity desktop will look like in this forthcoming release codenamed Natty Narwhal. I, for one, have been quite interested based upon the terrible Unity experience in Ubuntu 10.10 Netbook, so I fired up the latest Ubuntu Natty daily LiveCD released this morning. Here are some screenshots of the new Ubuntu Unity desktop as it stands in Natty Alpha 1 along with screenshots of Natty's classic GNOME desktop.
There's been a number of individuals and organizations asking us about benchmarks of Red Hat Enterprise Linux 6.0, which was released earlier this month and we had benchmarked beta versions of RHEL6 in past months. For those interested in benchmarks of Red Hat's flagship Linux operating system, here are some of our initial benchmarks comparing the official release of Red Hat Enterprise Linux 6.0 to Red Hat Enterprise Linux 5.5, openSUSE, Ubuntu, and Debian.
Recently we published benchmarks of Debian with the Etch, Lenny, and Squeeze releases. This is as far back as we could benchmark before hitting the 2.4 Linux kernel and running into hardware compatibility issues and other problems, considering Debian GNU/Linux doesn't seen an official release nearly as often as Ubuntu, Fedora, or most other distributions. We have now carried out a similar process, but on the Fedora side, and here we were able to go all the way back to the 2004 release of Fedora Core 3. Here are benchmarks of Fedora Core 3 with every release up through the recent release of Fedora 14.
Earlier today we put out benchmarks of ZFS on Linux via a native kernel module that will be made publicly available to bring this Sun/Oracle file-system over to more Linux users. Now though as a bonus we happen to have new benchmarks of the latest OpenSolaris-based distributions, including OpenSolaris, OpenIndiana, and Augustiner-Schweinshaxe, compared to PC-BSD, Fedora, and Ubuntu.
With Debian 6.0 "Squeeze" set to be released in the coming months, we have decided to run a set of benchmarks looking at the performance of Debian 6.0 across different sub-systems relative to the performance of Debian 5.0 "Lenny" and Debian 4.0 "Etch" to see how this new release may stack up.
Earlier today there was the unexpected surprise of Oracle releasing Solaris 11 Express. There wasn't any public betas or preview releases of Oracle Solaris 11 Express and the last time we got to look at anything new from the OpenSolaris code-base was months ago before Oracle decided to dismantle that once promising open-source Sun project. In the hours following the release of Oracle Solaris 11 Express we tried it out on a few different test systems. Here is a brief, visual tour of Oracle Solaris 11 Express for those interested.
Intel and Nokia last week rolled out MeeGo 1.1, which is now officially available for Intel Atom netbooks, the N900 handset, and in-vehicle "infotainment" systems. The netbook spin of MeeGo 1.1 is out there to compete with the likes of Ubuntu 10.10 Netbook Edition, which was released just shy of a month ago. While nothing radically has changed with MeeGo 1.1 compared to the initial MeeGo 1.0 release from earlier this year, the software stack is updated so for the past few days we have begun conducting a performance comparison between MeeGo 1.1 and Ubuntu 10.10 Netbook. Here are some of our initial findings.
Earlier this month we delivered Ubuntu 10.10 benchmarks from some different hardware comparing the performance of this "Maverick Meerkat" release to that of Ubuntu 9.10 and 10.04.1 LTS. The results were interesting, but since then we have had the time to complete additional tests. In this benchmarking roundabout, we decided to see how the performance of every release from Ubuntu 8.04 LTS through the new Ubuntu Linux release performs when tested in a virtualized environment using Linux's KVM virtualization. Here are the virtualized guest results for Ubuntu 8.04.4 LTS, 8.10, 9.04, 9.10, 10.04.1 LTS, and 10.10.
Being developed since 2007 and integrated in Ubuntu since 2008 with their Ubuntu 8.04 LTS release has been Wubi, the Windows-based Ubuntu Installer. While most Linux users tend to install Ubuntu using the LiveCD or the alternate CD installer, by using Wubi you can setup a full desktop from within Microsoft Windows. Wubi places Ubuntu into a disk image still residing on the Windows partition, thereby making it easy to install and remove without risking any problems of messing up your drive's partitions. While Wubi may lower the barrier for entry to trying out an Ubuntu Linux desktop, it does not come without some performance penalties associated to using the loop-mounted device stored on the Microsoft file-system.
As was reported recently, the Debian GNU/kFreeBSD port now has limited support for handling ZFS file-systems and its stock kernel has been upgraded against that of FreeBSD 8.1. Due to the upgraded kernel we ran a quick set of benchmarks to see how the performance of Debian GNU/kFreeBSD to that of Debian Linux.
With Ubuntu 10.10 having been released yesterday on the 10th of October, many Ubuntu users will be upgrading to this latest release in the coming days. However, for those that are concerned about the performance of this latest release that is codenamed the Maverick Meerkat, here are some benchmarks comparing its performance to Ubuntu 10.04.1 LTS as well as last October's Ubuntu 9.10 release.
The last time we closely examined the boot performance of Fedora Linux was in 2008 when comparing the boot times from Fedora Core 4 through Fedora 8. However, with more distributions taking pride in recent months over shortening their boot time -- with Canonical for example having worked towards a ten second Ubuntu boot time -- we decided to see how long it's taking Fedora to put its hat on these days. With the three Intel notebooks we used from our recent Fedora power consumption review, we measured the boot times using Bootchart on the Fedora 10, 11, 12, 13, and 14 Alpha releases.
With the release of Nexenta Core Platform 3.0 a few weeks back we decided to run some benchmarks of this operating system against PC-BSD 8.1, OpenSolaris b134, and Ubuntu 10.04.1 LTS. For those unfamiliar with Nexenta Core Platform, it is an operating system that combines the OpenSolaris kernel with a Linux user-land provided by the Ubuntu 8.04 LTS "Hardy Heron" package repository, complete with apt-get support for easy package installation.
Yesterday we looked at the performance of Apple's "Snow Leopard Graphics Update" for Mac OS X 10.6.4 designed to enhance both the image quality and rendering performance for OpenGL games and applications. For testing their graphics update we benchmarked Mac OS X 10.6.2, 10.6.3, 10.6.4, and 10.6.4 with the Snow Leopard Graphics Update 1.0 installed and benchmarked the Apple OpenGL performance against Ubuntu Linux. The results were mixed showing Apple still has room to optimize their OpenGL stack compared to NVIDIA's Linux implementation and in not all areas did this package update result in performance enhancements. After we finished that OpenGL comparison, we decided to see how the OpenCL performance compares between Mac OS X 10.6.4 and Ubuntu Linux 10.04.1 LTS. We tested the Open Computing Language on both the Intel Core 2 Duo CPU and on the NVIDIA GPU.
While our primary focus at Phoronix is on providing Linux benchmarks, we do enjoy trying out and benchmarking other operating systems like FreeBSD, Solaris, and Mac OS X. When Apple originally launched Mac OS X 10.6 "Snow Leopard" we were the first to provide detailed Mac OS X 10.6 benchmarks compared to Mac OS X 10.5 and also how Apple's new operating system at the time compared to Linux. We have continued to monitor the performance of Snow Leopard and found that some point releases had introduced some regressions and we have compared the performance of Mac OS X 10.6 to Windows 7 and Ubuntu 10.04 LTS. With Apple's release last week of the "Snow Leopard Graphics Update 1.0" that is reported to bring "stability and performance fixes for graphics applications and games in Mac OS X", our interest was piqued and we set out to run a new set of Apple OpenGL benchmarks. In this article we are looking at the OpenGL performance of Mac OS X 10.6, 10.6.2, 10.6.3, 10.6.4, and 10.6.4 with this graphics update installed.
At the beginning of this month we published workstation benchmarks comparing Windows 7 to Ubuntu Linux. In those tests, which were a continuation of tests from earlier this year when looking to see whether Windows 7 is faster than Ubuntu 10.04 and how fast is Windows compared to Mac OS X and Linux, the two operating systems performed quite closely in our workstation tests with only a few exceptions. Today, however, we are back to looking at the Linux vs. Windows performance of the Lenovo ThinkPad W510 and this time we are looking at the OpenGL gaming performance between Windows 7 Professional and Ubuntu 10.04 LTS.
As I alluded to recently, the second round of Windows 7 vs. Linux benchmarks -- with the first round consisting of Is Windows 7 Actually Faster Than Ubuntu 10.04 and Mac OS X vs. Windows 7 vs. Ubuntu benchmarks -- are currently being done atop a Lenovo ThinkPad W510 notebook that is quite popular with business professionals. With the high-end ThinkPad W510 boasting a dual quad-core Intel Core i7 CPU with Hyper-Threading plus a NVIDIA Quadro FX 880M graphics processor, we began this second round of cross-platform benchmarks by running a set of workstation tests. In this article we are mainly looking at the workstation graphics (via SPECViewPerf) performance along with some CPU/disk tests.
Traditionally at Phoronix we have stayed away from publishing benchmarks of Gentoo and similar source-based distributions for the lack of them having a standard or "stock" configuration for which one can easily replicate our tested software stack due to all of the different variables that come into play so the value of these benchmarks are much less compared to those distributions providing pre-compiled binaries for a standardized set of packages. However, satisfying a number of requests, we are publishing such benchmarks today. Rather than using Gentoo itself for benchmarking, we are using Calculate Linux Desktop, which is Gentoo-based while providing a very nice "out of the box" experience, i686 and x86_64 binaries, and overall is a polished and user-friendly Gentoo experience.
Back in January, we published the first benchmarks of Debian GNU/kFreeBSD: the spin of Debian that replaces the Linux kernel with the FreeBSD kernel while retaining most of the same GNU user-land and it uses the GNU C library. With those original tests comparing Debian GNU/Linux to Debian GNU/kFreeBSD, the Linux version ended up winning in 18 of the 27 tests. However, over the past six months, the Debian GNU/kFreeBSD port has matured and it's also moved to using the FreeBSD 7.3 kernel by default (compared to 7.2 back in January) and the FreeBSD 8.0 kernel is also emerging as a viable option that can be obtained using Debian's package management system. Today we have updated test numbers looking at the performance of Debian with the FreeBSD kernel using two different notebooks where we ran the latest Debian GNU/kFreeBSD packages with both the FreeBSD 7.3 and 8.0 kernels, Debian GNU/Linux with the Linux 2.6.32 kernel, and then finally we tested the pure FreeBSD 7.3 and FreeBSD 8.0 operating systems.
Following yesterday's release of openSUSE 11.3 we tested this updated Linux operating system that's sponsored by Novell on an Intel Atom netbook and compared the performance to that of Ubuntu 10.04 LTS and Fedora 13. Here are the results.
618 operating systems articles published on Phoronix.