Linked by cloud on Sat 27th Oct 2012 01:05 UTC
A new version of the real-time Linux scheduler called SCHED_DEADLINE has been released on the Linux Kernel Mailing List. For people who missed previous submissions, it consists of a new deadline-based CPU scheduler for the Linux kernel with bandwidth isolation (resource reservation) capabilities. It supports global/clustered multiprocessor scheduling through dynamic task migrations. This new version takes into account previous comments/suggestions and is aligned to the latest mainline kernel. A video about SCHED_DEADLINE is also available on YouTube.
Thread beginning with comment 540252
To view parent comment, click here.
To read all comments associated with this story, please click here.
To view parent comment, click here.
To read all comments associated with this story, please click here.
RE[3]: lie-nux at it again.
by Gullible Jones on Sat 27th Oct 2012 17:44
in reply to "RE[2]: lie-nux at it again."
Member since:2006-05-23
You're right, my mistake. For the Bad Things to happen, bs has to be set to something between physical RAM and total (physical + virtual) memory.
That said, I have never seen large writes fail to produce a noticeable slowdown. Not on an HDD anyway, I'm not sure about SSDs. I suspect that slowdowns during big writes are unavoidable on normal-spec desktops.
RE[3]: lie-nux at it again.
by WereCatf on Sat 27th Oct 2012 21:49
in reply to "RE[2]: lie-nux at it again."
Member since:2006-02-15
You sure? I get
dd: memory exhausted by input buffer of size 4294967296 bytes (4,0 GiB)
Lowering to bs=1G, dd will complete without much noticeable slowdown.
dd: memory exhausted by input buffer of size 4294967296 bytes (4,0 GiB)
Lowering to bs=1G, dd will complete without much noticeable slowdown.
Well, that is actually the expected behaviour on an average desktop-oriented distro. Of course allocating 4 gigabytes of contiguous memory on a system that do not have that much is going to slow down or fail, you can perfectly well try that on Windows and OSX and get exactly the same thing.
Now, before you go ahead and try to say this is a fault in Linux I have to enlighten you that it's actually a perfectly solveable problem. Forced pre-emption enabled in the kernel, a proper I/O scheduler and limiting either I/O or memory-usage per process or per user will solve that thing in a nice, clean way, without breaking anything in userland and provide for a functional, responsive system even with such a dd going in the background. If you're interested peruse the kernel documentation or Google around, there's plenty of documentation on exactly this topic.
These are, however, not used on desktop systems because usually desktop systems are only utilized by one person at a time and they do not have the need for such and therefore it's rather misguided to even complain about that -- these are features that are aimed at enterprise servers and require some tuning for your specific needs.
EDIT: Some reading for those who are interested:
http://en.wikipedia.org/wiki/Cgroups
http://git.kernel.org/?p=linux/kernel/git/torvalds/linux-2.6.git;a=...
http://git.kernel.org/?p=linux/kernel/git/torvalds/linux-2.6.git;a=...
Edited 2012-10-27 21:56 UTC
Features
Linked by Thom Holwerda on 06/13/13 14:35 UTC
The third and final WWDC product I want to talk about is - of course - OS X 10.9 Mavericks. While iOS 7 was clearly the focus of this year's WWDC, its venerable desktop counterpart certainly wasn't left behind. Apple announced OS X 10.9 Mavericks, the first OS X release not to carry the name of a big cat.
Linked by Thom Holwerda on 06/11/13 17:07 UTC
We already talked about iOS 7 yesterday (after a night of sleep, it's only looking worse and worse - look at this, for Fiona's sake!), so now it's time to talk about the downright stunning and belly flutters-inducing new Mac Pro. As former owner and huge, huge, huge fan of the PowerMac G4 Cube - I haven't been this excited about an Apple product since, well, I would say the iMac G4. This is the Apple I used to love.
Linked by Thom Holwerda on 06/10/13 23:13 UTC
Apple held its big keynote event thing at WWDC earlier this evening, but since I was away with friends I've had to read up on it later in the evening. The company announced iOS 7, OS X 10.9 Mavericks, and they gave a preview of the new Mac Pro. Especially the Mac Pro impressed me, and while iOS 7's new Holo/Metro-inspired theme looks messy and garish to me, I do commend Apple for finally breaking the mold. This news item will focus on iOS 7 - I'll dive into the Mac Pro and OS X 10.9 tomorrow (it's late here now).
Linked by Thom Holwerda on 06/08/13 14:57 UTC
And yes, the PRISM scandal is far, far from over. More and more information keeps leaking out, and the more gets out, the worse it gets. The companies involved have sent out official statements - often by mouth of their CEOs - and what's interesting is that not only are these official statements eerily similar to each other, using the same terms clearly designed by lawyers, they also directly contradict new reports from The New York Times. So, who is lying?
Linked by Thom Holwerda on 06/07/13 11:40 UTC
This story is getting bigger and bigger. Even though most Americans probably already knew, it is now official: the United States government, through its National Security Agency, is collecting the communications and data of all American citizens, and of non-Americans using American services, through a wide collaboration with the large companies in technology, like Apple, Google, Microsoft, Facebook, and so on. Interestingly enough, the NSA itself, as well as the US government, have repeatedly and firmly denied this massive spying on Americans and non-Americans took place at all.
Linked by Thom Holwerda on 06/04/13 12:45 UTC
Ah, patents - the never-ending scourge of the technology industry. Whether wielded by companies who don't actually make any products, or large corporations who abuse them because they can't compete in the market place or because they're simply jerks, they do the industry a huge disservice and are simply plain dangerous. According to The Wall Street Journal (circumvention link), president Obama is about to take several executive actions to address patent trolls - which may seem like a good idea, but I am very worried that all this will do is strengthen the positions of notorious patent system abusers such as Apple and Microsoft.
Linked by nfeske on 05/31/13 10:12 UTC
With version 13.05, the developers of the Genode OS Framework take measures to ensure that Genode continues to scale well with a growing number of users and the steadily broadening platform coverage. Further highlights are the improved SoC support for Exynos 5, OMAP4, Raspberry Pi, i.MX, and new components for realizing headless systems.
Linked by Thom Holwerda on 05/29/13 16:59 UTC
At the D11 conference, Apple CEO Tim Cook once again took the stage to be interviewed by Walt Mossberg and Kara Swisher. While most of the interview can be replicated by picking and reading 10 random Apple fanblog stories - there were still a number of very interesting things that warrant some closer scrutiny.
Linked by Thom Holwerda on 05/24/13 17:26 UTC
So, the Xbox One disaster continues. Microsoft's policy for dealing with the used games market has reportedly leaked - and it's a clear and direct attack to destroy the used games market. Prices for used games will be set at the retail value of a new game, and retailers have to hook into Microsoft's computer systems and comply with Microsoft's terms and conditions.
Linked by Thom Holwerda on 05/21/13 21:38 UTC
At an event earlier today, Microsoft unveiled the next Xbox - the third model, but confusingly named Xbox One. The big focus was TV, integrated Kinect, and all the other stuff we all expected to be forced down our throats. I think it took them 25 minutes to actually come to what should be the core of the story: gaming. Nothing groundbreaking in the gaming department, except for how Microsoft intends to handle the used games market and borrowing games from friends: pay up, buddy!More Features »
Sponsored Links
Member since:
2005-11-14
You sure? I get
dd: memory exhausted by input buffer of size 4294967296 bytes (4,0 GiB)
Lowering to bs=1G, dd will complete without much noticeable slowdown.