http://permalink.gmane.org/gmane.linux.distributions.emc.devel hourly 1 1901-01-01T00:00+00:00 http://gmane.org/img/gmane-25t.png http://gmane.org http://permalink.gmane.org/gmane.linux.distributions.emc.devel/6728 <pre>On Tuesday, May 22, 2012 04:43:44 PM dave did opine: Very interesting. Cost? Cheers, Gene </pre> gene heskett 2012-05-22T20:44:14 http://permalink.gmane.org/gmane.linux.distributions.emc.devel/6727 <pre> stock RTAI kernel running from the linuxcnc livecd -- I'm remembering 7 microseconds max when I was running java code from a cdrom. I always wondered if working over the kernel a little might help some, but that's hard to beat Eric Keller Boalsburg, Pennsylvania ------------------------------------------------------------------------------ Live Security Virtual Conference Exclusive live event will cover all the ways today's security and threat landscape has changed and how IT managers can respond. Discussions will include endpoint security, mobile security and the latest in malware threats. http://www.accelacomm.com/jaw/sfrnl04242012/114/50122263/ </pre> Eric Keller 2012-05-22T20:31:22 http://permalink.gmane.org/gmane.linux.distributions.emc.devel/6726 <pre>On Tue, 22 May 2012 19:38:01 +0100 andy pugh &lt;bodgesoc&lt; at &gt;gmail.com&gt; wrote: I had the impression we were dealing with latencies somewhat longer. I learn something everyday if I'm not careful. ;-) Dave ------------------------------------------------------------------------------ Live Security Virtual Conference Exclusive live event will cover all the ways today's security and threat landscape has changed and how IT managers can respond. Discussions will include endpoint security, mobile security and the latest in malware threats. http://www.accelacomm.com/jaw/sfrnl04242012/114/50122263/ _______________________________________________ Emc-developers mailing list Emc-developers&lt; at &gt;lists.sourceforge.net https://lists.sourceforge.net/lists/listinfo/emc-developers </pre> dave 2012-05-22T19:50:43 http://permalink.gmane.org/gmane.linux.distributions.emc.devel/6725 <pre>That's RTLinux, _patented_ real-time extension to Linux, was a pain to go around for at least a decade. On Tue, May 22, 2012 at 10:38 PM, andy pugh &lt;bodgesoc-Re5JQEeQqe8AvxtiuMwx3w&lt; at &gt;public.gmane.org&gt; wrote: ------------------------------------------------------------------------------ Live Security Virtual Conference Exclusive live event will cover all the ways today's security and threat landscape has changed and how IT managers can respond. Discussions will include endpoint security, mobile security and the latest in malware threats. http://www.accelacomm.com/jaw/sfrnl04242012/114/50122263/ </pre> Alexey Starikovskiy 2012-05-22T19:17:37 http://permalink.gmane.org/gmane.linux.distributions.emc.devel/6724 <pre> ... Those number sound similar to RTAI with the Atom boards. </pre> andy pugh 2012-05-22T18:38:01 http://permalink.gmane.org/gmane.linux.distributions.emc.devel/6723 <pre>the whole enchilada is at: http://www.prnewswire.com/news-releases/fsmlabs-showcases-breakthrough-fast-real-time-linux-for-amd-dual-core-processors-at-esc-boston-54936777.html Synopsis: " Performance Edge - Hard Real-time "AMD processors offer great price/performance, but most embedded OSes and tools can't take advantage of core AMD CPU capabilities," comments Victor Yodaiken, president and CEO of FSMLabs. "FSMLabs customers today build and deploy applications with hard real-time performance on AMD 64 bit dual-core Opterons. They also create products ranging from s/w radios and automobile diagnostics built on AMD Alchemy CPUs to VoIP gateways running on AMD Geode/Elan processors." On an AMD Opteron 265 dual core system, RTLinux guarantees interrupt latencies of no more than 5 microseconds with scheduling jitter of no more than 8 microseconds even with Linux under heavy load. These industry-leading times can be further reduced with FSMLabs timer advance and processor reservation </pre> dave 2012-05-22T18:33:42 http://permalink.gmane.org/gmane.linux.distributions.emc.devel/6722 <pre> Oh, of course. And I do but I have instructed the list server not to echo my messages back to me. Hence, I couldn't say if the file were included or not. Since others also use the digest mode, it is obviously safer not to depend on a working file-attachment function. I used to know that:-) Thanks, Stuart. Regards, Kent ------------------------------------------------------------------------------ Live Security Virtual Conference Exclusive live event will cover all the ways today's security and threat landscape has changed and how IT managers can respond. Discussions will include endpoint security, mobile security and the latest in malware threats. http://www.accelacomm.com/jaw/sfrnl04242012/114/50122263/ </pre> Kent A. Reed 2012-05-22T01:45:12 http://permalink.gmane.org/gmane.linux.distributions.emc.devel/6721 <pre>possibly because I don't get the developers list as individual emails </pre> Stuart Stevenson 2012-05-22T01:30:40 http://permalink.gmane.org/gmane.linux.distributions.emc.devel/6720 <pre> Which is fine, Andy. I wonder how you got it and Stuart didn't? Regards, Kent ------------------------------------------------------------------------------ Live Security Virtual Conference Exclusive live event will cover all the ways today's security and threat landscape has changed and how IT managers can respond. Discussions will include endpoint security, mobile security and the latest in malware threats. http://www.accelacomm.com/jaw/sfrnl04242012/114/50122263/ </pre> Kent A. Reed 2012-05-21T23:07:11 http://permalink.gmane.org/gmane.linux.distributions.emc.devel/6719 <pre> I got the graphic as an attachment. I just couldn't think of much to say about it. </pre> andy pugh 2012-05-21T22:58:25 http://permalink.gmane.org/gmane.linux.distributions.emc.devel/6718 <pre> Aw snap. I forgot that only text files can be attached to messages passing through our mail list server. Usually it's my short-term memory that's faulty, but this is definitely a lapse in long-term memory. I've posted a png image at https://sites.google.com/site/manisbutareed Thanks, Stuart. Regards, Kent ------------------------------------------------------------------------------ Live Security Virtual Conference Exclusive live event will cover all the ways today's security and threat landscape has changed and how IT managers can respond. Discussions will include endpoint security, mobile security and the latest in malware threats. http://www.accelacomm.com/jaw/sfrnl04242012/114/50122263/ </pre> Kent A. Reed 2012-05-21T22:37:23 http://permalink.gmane.org/gmane.linux.distributions.emc.devel/6717 <pre>So, you mean, still the host OS and Hardware would need some degree of tunning as well. I presume tunning similar to that needed for RTAI Xenomai or PREEMPT_RT patch. But if such issues are solved, it looks that preemption associated overload can be reduced greatly using very simple mechanisms can be used Javier On Mon, May 21, 2012 at 1:54 PM, Alexey Starikovskiy &lt;aystarik-Re5JQEeQqe8AvxtiuMwx3w&lt; at &gt;public.gmane.org&gt;wrote: ------------------------------------------------------------------------------ Live Security Virtual Conference Exclusive live event will cover all the ways today's security and threat landscape has changed and how IT managers can respond. Discussions will include endpoint security, mobile security and the latest in malware threats. http://www.accelacomm.com/jaw/sfrnl04242012/114/50122263/ </pre> Javier Ros 2012-05-21T13:10:53 http://permalink.gmane.org/gmane.linux.distributions.emc.devel/6716 <pre>Actually I will add that I know a group that is releasing something called NIX -- which last I heard they had a core locking mechanism, but I doubt that there was any effort spent on hard real-time constraints. On Mon, 21 May 2012 08:03:55 -0400, EBo wrote: ------------------------------------------------------------------------------ Live Security Virtual Conference Exclusive live event will cover all the ways today's security and threat landscape has changed and how IT managers can respond. Discussions will include endpoint security, mobile security and the latest in malware threats. http://www.accelacomm.com/jaw/sfrnl04242012/114/50122263/ _______________________________________________ Emc-developers mailing list Emc-developers&lt; at &gt;lists.sourceforge.net https://lists.sourceforge.net/lists/listinfo/emc-developers </pre> EBo 2012-05-21T12:20:58 http://permalink.gmane.org/gmane.linux.distributions.emc.devel/6715 <pre>I never said it was easy. Hence potential PhD level material. On Mon, 21 May 2012 15:54:31 +0400, Alexey Starikovskiy wrote: ------------------------------------------------------------------------------ Live Security Virtual Conference Exclusive live event will cover all the ways today's security and threat landscape has changed and how IT managers can respond. Discussions will include endpoint security, mobile security and the latest in malware threats. http://www.accelacomm.com/jaw/sfrnl04242012/114/50122263/ _______________________________________________ Emc-developers mailing list Emc-developers&lt; at &gt;lists.sourceforge.net https://lists.sourceforge.net/lists/listinfo/emc-developers </pre> EBo 2012-05-21T12:03:55 http://permalink.gmane.org/gmane.linux.distributions.emc.devel/6714 <pre>Other cores could still launch DMA or even SMI and screw the RT on your core. On Mon, May 21, 2012 at 3:41 PM, EBo &lt;ebo-doD3EReIBWJBDgjK7y7TUQ&lt; at &gt;public.gmane.org&gt; wrote: ------------------------------------------------------------------------------ Live Security Virtual Conference Exclusive live event will cover all the ways today's security and threat landscape has changed and how IT managers can respond. Discussions will include endpoint security, mobile security and the latest in malware threats. http://www.accelacomm.com/jaw/sfrnl04242012/114/50122263/ </pre> Alexey Starikovskiy 2012-05-21T11:54:31 http://permalink.gmane.org/gmane.linux.distributions.emc.devel/6713 <pre>Core locking programs is part of the state of the art in OS research. I know that there are Linux variants which are doing this, but it will likely be awhile before it goes mainstream. Knowing the people I do working on this I imagine that it will actually go mainstream. Making all this work correctly is a non trivial task, and if you wanted to jump into the middle of this it is likely worth a MS and possibly even a PhD in computer architecture. That being said, there might be some entry level stuff that can be hacked along these lines. EBo -- On Mon, 21 May 2012 12:58:40 +0200, Javier Ros wrote: ------------------------------------------------------------------------------ Live Security Virtual Conference Exclusive live event will cover all the ways today's security and threat landscape has changed and how IT managers can respond. Discussions will include endpoint security, mobile security and the latest in malware threats. http://www.accelacomm.com/jaw/sfrnl04242012/114/50122263/ </pre> EBo 2012-05-21T11:41:09 http://permalink.gmane.org/gmane.linux.distributions.emc.devel/6712 <pre>Hi, What about isolate a core in todays multicore cpu, to do the RT work, using a custom support layer avoiding using linux itself, RTAI or Xenomai? Even ARMs are going multicore today. I presume that you can have the NON-rt running in standard Linux user land, and then communicate through shared memory with the isolated core. I don't know much about the architecture, but I presume that the isolated core can probably generate its own timer interrupts. I presume that the kernel probably can ignore a hardware card like a parallel port and lend its responsibility/ownership to the core devoted to RT. I'm not an expert but it looks like it can not be really difficult to make HAL's RT part to tun isolated on that core. Most setups are using two threads, and lots just one. A custom support layer without RTAI or XENOMAI can be developed. Also I presume that there is some Open Source POXIX like RTOS, that can be easier o use than to develop. Such a philosophy, if possible, will make LinuxCNC pretty independen</pre> Javier Ros 2012-05-21T10:58:40 http://permalink.gmane.org/gmane.linux.distributions.emc.devel/6711 <pre>Fixed. John On 5/20/2012 8:39 AM, Chris Morley wrote: ------------------------------------------------------------------------------ Live Security Virtual Conference Exclusive live event will cover all the ways today's security and threat landscape has changed and how IT managers can respond. Discussions will include endpoint security, mobile security and the latest in malware threats. http://www.accelacomm.com/jaw/sfrnl04242012/114/50122263/ </pre> John Thornton 2012-05-20T17:57:59 http://permalink.gmane.org/gmane.linux.distributions.emc.devel/6710 <pre>Direct-value pins are all current, used and not depreciated. I added those pins, nobody has complained AFAIK. Thanks for answering Kim and John Chris M Sent from my BlackBerry device on the Rogers Wireless Network -----Original Message----- From: Kim Kirwan &lt;Kim-JM4nw2KYq+KaMJb+Lgu22Q&lt; at &gt;public.gmane.org&gt; Date: Sun, 20 May 2012 07:30:06 To: &lt;emc-developers-5NWGOfrQmneRv+LV9MX5uipxlwaOVQ5f&lt; at &gt;public.gmane.org&gt; Subject: Re: [Emc-developers] halui -feed-override.direct-value manual comment Sorry, I can't help much with this, even though it's my edit. I remember that I thought several of those items mentioned were a little unclear, and I asked for clarification from one of the gurus, and I was given that information as an additional aside. So I put it in as a footnote. The rest of it I must have thought was helped by the clarification, since apparently I decided to leave the rest mostly as it was. (It all seemed real clear immediately after he explained it... ;) I'll think about this and see if there</pre> Chris Morley 2012-05-20T13:39:31 http://permalink.gmane.org/gmane.linux.distributions.emc.devel/6709 <pre>Sorry, I can't help much with this, even though it's my edit. I remember that I thought several of those items mentioned were a little unclear, and I asked for clarification from one of the gurus, and I was given that information as an additional aside. So I put it in as a footnote. The rest of it I must have thought was helped by the clarification, since apparently I decided to leave the rest mostly as it was. (It all seemed real clear immediately after he explained it... ;) I'll think about this and see if there's anything more I can do to improve that section further. If anyone else wants to jump in on this, that's fine too. Also, thanks to Chris Morley for mentioning the absence of the max-velocity.direct-value pin. Does anyone know if that one is also affected by the above-mentioned released/withdrawn footnote? The footnote is in ~/linuxcnc-dev/docs/src/gui/halui.txt near line 53, in v2.5_branch, if anyone is still interested. To show my edit where I added the footnote that JT refers</pre> Kim Kirwan 2012-05-20T07:30:06 http://permalink.gmane.org/gmane.linux.distributions.emc.devel/6708 <pre> Right. I missed that it was Jon asking... my bad... ------------------------------------------------------------------------------ Live Security Virtual Conference Exclusive live event will cover all the ways today's security and threat landscape has changed and how IT managers can respond. Discussions will include endpoint security, mobile security and the latest in malware threats. http://www.accelacomm.com/jaw/sfrnl04242012/114/50122263/ _______________________________________________ Emc-developers mailing list Emc-developers&lt; at &gt;lists.sourceforge.net https://lists.sourceforge.net/lists/listinfo/emc-developers </pre> EBo 2012-05-19T21:20:07 Search the mailing list at Gmane query http://search.gmane.org/?group=$group=gmane.linux.distributions.emc.devel