Ingo Molnar released a new patchset titled the 'Modular Scheduler Core and Completely Fair Scheduler'. He explained, "this project is a complete rewrite of the Linux task scheduler. My goal is to address various feature requests and to fix deficiencies in the vanilla scheduler that were suggested/found in the past few years, both for desktop scheduling and for server scheduling workloads."
To read all comments associated with this story, please click here.
Member since:2006-07-15
I am by no means an expert on any of this, but my guess would be that if a schedular is completely fair, then virtualization wouldn't be too good off, as the virtualized box would get one tick / whatever, no exceptions. All the processes in that box would have to run off that one tick (basically).
Of course, I could be completely wrong, in that case ignore me.
Member since:2006-01-04
When they say "Completely fair", they actually mean more fair than equal. The processor time is divided in a fair way so that latency sensitive apps can be prioritised over more throughput apps. What you have described is equal timeslices (except nobody divides it as small as single ticks) which can be used on the current kernel, I believe.
Member since:2005-07-24
"""
I know that Linux kernels with HZ=1000 option are rather slow in Virtualization environments and I would like to know how this new scheduler will perform in such Virtual (VMware/VirtualBox/...) environments.
"""
I may be misunderstanding your question. But if you are speaking of performance degradation due to excessive timer interrupts when many instances of the kernel are running, I think that the really exciting news on this front lies not with the scheduler, but with the tickless kernel patch, applied to 2.6.21-rc1, and due to be released in a stable kernel possibly as soon as next week.
But the tickless patch itself is only the beginning. Next will follow patches with the batching of interrupts in mind, so that more things get scheduled to be done during one wake up period of the processor (virtual or otherwise), resulting in even fewer interrupts.
edit: Just a few more notes. Tickless in 2.6.21 will be an option, not the default. It is only available on x86 (32 bit), but should be available on other architectures shortly. FC7 will have tickless on by default. My laptop has gone tickless (2.6.21-rc6) and I've had no problems so far.
Edited 2007-04-23 04:03
The Verge pointed me to a blog post by Leap Motion - which reveals how their Kinect-like motion control works with Windows 8. "From the second you plug in your Leap Motion Controller, you'll be able to browse the web and interact with your computer just by moving your hands and fingers in the air. With Leap Motion technology and Windows, you can do everything that's possible with multi-touch inputs - without actually touching anything. This also means that existing applications in Windows 7 and 8 will respond to your natural hand and finger movements. Soon, we'll show you how Leap Motion will work with Mac OS X." Quite cool.
PocketNow interviews Marc Dillon, and there's an interesting note about why Jolla is keeping the display properties under wraps: "We're leaving some of those details out because we do understand that there are a lot of really big players in the market and they tend to take certain components in the market and dominate them. We created the ability to actually be able to run Sailfish on multiple hardware displays and be able to swap components, so this is part of the demand and supply planning phase. We are committed to this industrial design which is a 4.5-inch display, an 8 megapixel camera on the back and a front-facing camera at the front, and the exact specs of the display we'll provide when we're close to delivery." Something you rarely hear anything about.
"This is my NeXTstation Turbo Color booting the Mac System 7.1 Operating System using a hardware add-on called 'Daydream'. The Daydream has a Mac ROM and a few custom ICs in it and hooked up to the NeXTs DSP port. Turns your NeXT into a full fledged 68k powered Mac." So cool.
"The NetBSD Project is pleased to announce NetBSD 6.1, the first feature update of the NetBSD 6 release branch. It represents a selected subset of fixes deemed important for security or stability reasons, as well as new features and enhancements. Please note that all fixes in the prior security/bugfix updates (NetBSD 6.0.1 and 6.0.2) are also in 6.1."
"At the end of a week in which Electronic Arts confirmed it wasn't developing a thing for the Wii U, one of the software engineers in EA Sports' Canada studio, in a series of since-deleted tweets, disparaged the console as 'crap' and suggested Nintendo should give up on hardware altogether. 'The Wii U is crap. Less powerful than an Xbox 360. Poor online/store. Weird tablet', tweeted Bob Summerwill, listed as a senior software engineer at EA Canada, in a reply to a tweet posting a link about EA's no-Wii U news. 'Nintendo are walking dead at this point'." The Wii U is turning into the 21st century's Virtual Boy."In NixOS, the entire operating system - the kernel, applications, system packages, configuration files, and so on - is built by the Nix package manager from a description in a purely functional build language. The fact that it's purely functional essentially means that building a new configuration cannot overwrite previous configurations. Most of the other features follow from this." Interesting approach. A Linux distribution, sure, but with some very refreshing ideas about system configuration.
Appfour added, among other features, C/C++ support to its new version of AIDE. From Android-IDE, "Now you can write parts of your app or your whole app in C/C++ on your device. AIDE supports the Standard Android NDK toolchain (GCC 4.6 + Bionic, STL, ...). No changes are necessary if you want to build an app developed on a PC with Eclipse. C/C++ development is fully integrated: Build errors appear in the error list and files can easily be navigated to with Go to file. The editor supports C/C++ syntax highlighting."
Ars nails it: "The answer is that Google did announce what amounts to a fairly substantial Android update yesterday. They simply did it without adding to the update fragmentation problems that continue to plague the platform. By focusing on these changes and not the apparently-waiting-in-the-wings update to the core software, Google is showing us one of the ways in which it's trying to fix the update problem."
"It is good for programmers to understand what goes on inside a processor. The CPU is at the heart of our career. What goes on inside the CPU? How long does it take for one instruction to run? What does it mean when a new CPU has a 12-stage pipeline, or 18-stage pipeline, or even a 'deep' 31-stage pipeline? Programs generally treat the CPU as a black box. Instructions go into the box in order, instructions come out of the box in order, and some processing magic happens inside. As a programmer, it is useful to learn what happens inside the box. This is especially true if you will be working on tasks like program optimization. If you don't know what is going on inside the CPU, how can you optimize for it? This article is about what goes on inside the x86 processor's deep pipeline."
"It was the only moment I heard regret slip into Otellini's voice during the several hours of conversations I had with him. 'The lesson I took away from that was, while we like to speak with data around here, so many times in my career I've ended up making decisions with my gut, and I should have followed my gut,' he said. 'My gut told me to say yes.'" The world would've been a much different place - Apple would have been less dependant on Samsung for its chips, which probably would've meant less money for Samsung to develop its Galaxy business.
Member since:
2007-03-16
How about Virtualization/Emulation software ?
I know that Linux kernels with HZ=1000 option are rather slow in Virtualization environments and I would like to know how this new scheduler will perform in such Virtual (VMware/VirtualBox/...) environments.