Hello Dashesy, very good information are available at: https://www.osadl.org/Individual-system-data.qa-farm-data.0.html#c4630 Check out the latency plots and make your own conclusion. --Armin dashesy wrote:
I have tested the rt31 patch and everything seems great on my off-the-shelf high-end Xeon desktop so far. I will continue testing and let you know if I find any oopses or panics :) We are in the process of upgrading our embedded system, now based on an old ADEOS patch. In the first step we need to substitute our soon to be obsolete motherboard with a new long life industrial motherboard that works with -rt (as we all hope it will be all in the mainline). I know I will be going to a lengthy validation and testing phase to choose the right motherboard, one that is reliable (for a medical device), state-of-the-art (at least two cores) and of course -rt compliant (some indication about thing like SMI or hrtimer issues for example). There are few book and plenty of resources out there. "Building Embedded Linux Systems by Karim Yaghmour, et al" is a nice book, and linux-rt archives, LWN and LKML have been the ultimate source to keep up with the past (as much as I could) an learn the new. To find out what might cause problem or what to avoid when designing the system. It seems the manufacturers section of the OSADL Realtime QA Farm is a good starting point to look for motherboards if one is concerned about the latency plots, however, That would be great if there was some sort of -rt compliance certificate or tag, issued by OSADL (one organization that I can think of). I believe, this might generate some revenue for the project, and some ease of mind for developers who want to start a fresh design. I appreciate any comments or suggestion about the motherboard. Thanks dashesy -- To unsubscribe from this list: send the line "unsubscribe linux-rt-users" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
-- To unsubscribe from this list: send the line "unsubscribe linux-rt-users" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
