Re: [Emc-users] Latency test numbers confusing
Neil Baylis wrote: > OK, so I started up the computer, then waited 1/2 hour. Then I ran the > latency test for 1/2 hour with no "abuse", and the latency was below 7 > microseconds. I have plenty of other computers, so I certainly don't > need to be doing anything else on my EMC box when it's running EMC. > The problem is EMC, ITSELF, abuses the computer a bit by running a 3-D display in the Axis GUI. That takes considerable resources, and unless you will be running the GUI on another computer, or won't be using Axis, you need to simulate that load to get an accurate reading. Also, network interfaces can cause DMA block transfers and CPU interrupts. Clearly, you don't need video players, music players, etc. for CNC. Jon -- Throughout its 18-year history, RSA Conference consistently attracts the world's best and brightest in the field, creating opportunities for Conference attendees to learn about information security's most important issues through interactions with peers, luminaries and emerging and established companies. http://p.sf.net/sfu/rsaconf-dev2dev ___ Emc-users mailing list Emc-users@lists.sourceforge.net https://lists.sourceforge.net/lists/listinfo/emc-users
Re: [Emc-users] Latency test numbers confusing
On Thu, Jan 14, 2010 at 1:00 PM, Andy Pugh wrote: > 2010/1/14 Neil Baylis : >> >> Ah OK. The penny drops. When I get home tonight, I'll follow the >> directions to disable SMI and see what happens. > > It doesn't sound like SMI. That normally happens periodically. (in my > case it was every 64 seconds) You were correct. I followed the instructions for disabling SMI, and it made no difference. However, it seems reliably true that once you get past the two spikes, the latency is tolerable. I'm going to run that way for the time being, and see how it goes. If I notice problems, I'll investigate further. Neil -- Throughout its 18-year history, RSA Conference consistently attracts the world's best and brightest in the field, creating opportunities for Conference attendees to learn about information security's most important issues through interactions with peers, luminaries and emerging and established companies. http://p.sf.net/sfu/rsaconf-dev2dev ___ Emc-users mailing list Emc-users@lists.sourceforge.net https://lists.sourceforge.net/lists/listinfo/emc-users
Re: [Emc-users] Latency test numbers confusing
2010/1/14 Neil Baylis : > > Ah OK. The penny drops. When I get home tonight, I'll follow the > directions to disable SMI and see what happens. It doesn't sound like SMI. That normally happens periodically. (in my case it was every 64 seconds) > > Is SMI the facility that makes the fans speed up and slow down > according to how busy the system is? Or is that something else? That's something else, I think. Though SMI is involved in thermal management, I believe, and so you don't want to mess with it unless you are sure you need to. -- atp -- Throughout its 18-year history, RSA Conference consistently attracts the world's best and brightest in the field, creating opportunities for Conference attendees to learn about information security's most important issues through interactions with peers, luminaries and emerging and established companies. http://p.sf.net/sfu/rsaconf-dev2dev ___ Emc-users mailing list Emc-users@lists.sourceforge.net https://lists.sourceforge.net/lists/listinfo/emc-users
Re: [Emc-users] Latency test numbers confusing
Ah OK. The penny drops. When I get home tonight, I'll follow the directions to disable SMI and see what happens. Is SMI the facility that makes the fans speed up and slow down according to how busy the system is? Or is that something else? (My fans seem very dynamic, speeding up and slowing down at the drop of a hat. But if I run just the latency test, they run quiet and slow.) -- Throughout its 18-year history, RSA Conference consistently attracts the world's best and brightest in the field, creating opportunities for Conference attendees to learn about information security's most important issues through interactions with peers, luminaries and emerging and established companies. http://p.sf.net/sfu/rsaconf-dev2dev ___ Emc-users mailing list Emc-users@lists.sourceforge.net https://lists.sourceforge.net/lists/listinfo/emc-users
Re: [Emc-users] Latency test numbers confusing
Ah OK. The penny drops. When I get home tonight, I'll follow the directions to disable SMI and see what happens. Is SMI the facility that makes the fans speed up and slow down according to how busy the system is? Or is that something else? (My fans seem very dynamic, speeding up and slowing down at the drop of a hat. But if I run just the latency test, they run quiet and slow.) -- Throughout its 18-year history, RSA Conference consistently attracts the world's best and brightest in the field, creating opportunities for Conference attendees to learn about information security's most important issues through interactions with peers, luminaries and emerging and established companies. http://p.sf.net/sfu/rsaconf-dev2dev ___ Emc-users mailing list Emc-users@lists.sourceforge.net https://lists.sourceforge.net/lists/listinfo/emc-users
Re: [Emc-users] Latency test numbers confusing
2010/1/14 Neil Baylis : > What is SMI? System Management Interrupt. Wiki description: http://en.wikipedia.org/wiki/System_Management_Mode How to get round it in RTAI http://wiki.linuxcnc.org/cgi-bin/emcinfo.pl?FixingSMIIssues -- atp -- Throughout its 18-year history, RSA Conference consistently attracts the world's best and brightest in the field, creating opportunities for Conference attendees to learn about information security's most important issues through interactions with peers, luminaries and emerging and established companies. http://p.sf.net/sfu/rsaconf-dev2dev ___ Emc-users mailing list Emc-users@lists.sourceforge.net https://lists.sourceforge.net/lists/listinfo/emc-users
Re: [Emc-users] Latency test numbers confusing
OK, so I started up the computer, then waited 1/2 hour. Then I ran the latency test for 1/2 hour with no "abuse", and the latency was below 7 microseconds. I have plenty of other computers, so I certainly don't need to be doing anything else on my EMC box when it's running EMC. Neil -- Throughout its 18-year history, RSA Conference consistently attracts the world's best and brightest in the field, creating opportunities for Conference attendees to learn about information security's most important issues through interactions with peers, luminaries and emerging and established companies. http://p.sf.net/sfu/rsaconf-dev2dev ___ Emc-users mailing list Emc-users@lists.sourceforge.net https://lists.sourceforge.net/lists/listinfo/emc-users
Re: [Emc-users] Latency test numbers confusing
> On a side note I have just started testing a Dell Optiplex > GX520. When you first start the computer during the first 4 minutes there > are two 250,000 spikes in the test with or without SMI. So far they do not > repeat again even after the computer is on for several hours. Have had > similar results in the 120,000 range with a Optiplex GX260 that I am using > on a mill without any problems. May not be an issue, just have to warm the > computer up before cutting! > > Rick > What is SMI? Also, what graphics card are you using with the Dells? Neil -- Throughout its 18-year history, RSA Conference consistently attracts the world's best and brightest in the field, creating opportunities for Conference attendees to learn about information security's most important issues through interactions with peers, luminaries and emerging and established companies. http://p.sf.net/sfu/rsaconf-dev2dev ___ Emc-users mailing list Emc-users@lists.sourceforge.net https://lists.sourceforge.net/lists/listinfo/emc-users
Re: [Emc-users] Latency test numbers confusing
2010/1/14 Евгений Александрович : > Maybe the problem is CPU TERMAL TROLLING? > I tested one PC, which had BIOS without option to disable CPU TERMAL TROLLING. > I did not find any way how to use that PC with EMC2. > Sorry I don't know what that is. I guess it means my BIOS has no way of disabling it either. -- Throughout its 18-year history, RSA Conference consistently attracts the world's best and brightest in the field, creating opportunities for Conference attendees to learn about information security's most important issues through interactions with peers, luminaries and emerging and established companies. http://p.sf.net/sfu/rsaconf-dev2dev ___ Emc-users mailing list Emc-users@lists.sourceforge.net https://lists.sourceforge.net/lists/listinfo/emc-users
Re: [Emc-users] Latency test numbers confusing
On Thu, Jan 14, 2010 at 4:05 AM, rng3 wrote: > If the GUI latency test gives a result of how EMC will perform I always > wondered if "abusing the computer" during the test does not result in an > overly conservative number. I never use the computer that is running EMC > with any other program until the parts are done. (Am I the only one?) There > can be a dramatic difference between the latency test running by itself or > the test running with everything else we may be doing with the computer at > the same time. On a side note I have just started testing a Dell Optiplex > GX520. When you first start the computer during the first 4 minutes there > are two 250,000 spikes in the test with or without SMI. So far they do not > repeat again even after the computer is on for several hours. Have had > similar results in the 120,000 range with a Optiplex GX260 that I am using > on a mill without any problems. May not be an issue, just have to warm the > computer up before cutting! > > Rick > Yes, this is exactly what I'm seeing on the GX280. If I reset the latency test after those spiikes, I never see them again. I'm going to try starting the computer, but not running the test for half an hour or so to see what happens. Is there any procedure for tracking down the cause of these spikes? Neil -- Throughout its 18-year history, RSA Conference consistently attracts the world's best and brightest in the field, creating opportunities for Conference attendees to learn about information security's most important issues through interactions with peers, luminaries and emerging and established companies. http://p.sf.net/sfu/rsaconf-dev2dev ___ Emc-users mailing list Emc-users@lists.sourceforge.net https://lists.sourceforge.net/lists/listinfo/emc-users
Re: [Emc-users] Latency test numbers confusing
Maybe the problem is CPU TERMAL TROLLING? I tested one PC, which had BIOS without option to disable CPU TERMAL TROLLING. I did not find any way how to use that PC with EMC2. -Original Message- From: "rng3" To: "Enhanced Machine Controller \(EMC\)" Date: Thu, 14 Jan 2010 07:05:49 -0500 Subject: Re: [Emc-users] Latency test numbers confusing > If the GUI latency test gives a result of how EMC will perform I always > wondered if "abusing the computer" during the test does not result in an > overly conservative number. I never use the computer that is running EMC > with any other program until the parts are done. (Am I the only one?) There > can be a dramatic difference between the latency test running by itself or > the test running with everything else we may be doing with the computer at > the same time. On a side note I have just started testing a Dell Optiplex > GX520. When you first start the computer during the first 4 minutes there > are two 250,000 spikes in the test with or without SMI. So far they do not > repeat again even after the computer is on for several hours. Have had > similar results in the 120,000 range with a Optiplex GX260 that I am using > on a mill without any problems. May not be an issue, just have to warm the > computer up before cutting! > -- Throughout its 18-year history, RSA Conference consistently attracts the world's best and brightest in the field, creating opportunities for Conference attendees to learn about information security's most important issues through interactions with peers, luminaries and emerging and established companies. http://p.sf.net/sfu/rsaconf-dev2dev ___ Emc-users mailing list Emc-users@lists.sourceforge.net https://lists.sourceforge.net/lists/listinfo/emc-users
Re: [Emc-users] Latency test numbers confusing
If the GUI latency test gives a result of how EMC will perform I always wondered if "abusing the computer" during the test does not result in an overly conservative number. I never use the computer that is running EMC with any other program until the parts are done. (Am I the only one?) There can be a dramatic difference between the latency test running by itself or the test running with everything else we may be doing with the computer at the same time. On a side note I have just started testing a Dell Optiplex GX520. When you first start the computer during the first 4 minutes there are two 250,000 spikes in the test with or without SMI. So far they do not repeat again even after the computer is on for several hours. Have had similar results in the 120,000 range with a Optiplex GX260 that I am using on a mill without any problems. May not be an issue, just have to warm the computer up before cutting! Rick -- Throughout its 18-year history, RSA Conference consistently attracts the world's best and brightest in the field, creating opportunities for Conference attendees to learn about information security's most important issues through interactions with peers, luminaries and emerging and established companies. http://p.sf.net/sfu/rsaconf-dev2dev ___ Emc-users mailing list Emc-users@lists.sourceforge.net https://lists.sourceforge.net/lists/listinfo/emc-users
Re: [Emc-users] Latency test numbers confusing
The text mode latency tests in /usr/realtime* have a different structure and details than the graphical test. The graphical test more accurately reflects what emc's realtime performance will be. Besides involving additional emc code ("rtapi"), the graphical latency test is usually run with two realtime threads (1ms and 25us), while the text latency test is run with a single thread of 100us. That said, I don't personally recall seeing as big a difference as 100us vs 12us between the two tests. Jeff -- This SF.Net email is sponsored by the Verizon Developer Community Take advantage of Verizon's best-in-class app development support A streamlined, 14 day to market process makes app distribution fast and easy Join now and get one step closer to millions of Verizon customers http://p.sf.net/sfu/verizon-dev2dev ___ Emc-users mailing list Emc-users@lists.sourceforge.net https://lists.sourceforge.net/lists/listinfo/emc-users
[Emc-users] Latency test numbers confusing
I've been running the latency test from the applications menu as I experiment with my graphics setup. Today I discovered the command-line version, and ran that. What's confusing is that I get different results depending on which one I run. When I run the command-line version, the worst latency I ever see is about 12 microseconds. This seems fine. When I run the GUI version, it's more like 25 microseconds, but very occasionally I see numbers greater than 100 microseconds. This seems not so fine at all. Any idea what's going on here? Which numbers should I believe? Neil -- This SF.Net email is sponsored by the Verizon Developer Community Take advantage of Verizon's best-in-class app development support A streamlined, 14 day to market process makes app distribution fast and easy Join now and get one step closer to millions of Verizon customers http://p.sf.net/sfu/verizon-dev2dev ___ Emc-users mailing list Emc-users@lists.sourceforge.net https://lists.sourceforge.net/lists/listinfo/emc-users