On 02/05/2017 11:55 AM, Ran Shalit wrote: > On Sat, Feb 4, 2017 at 12:10 PM, Philippe Gerum <[email protected]> wrote: >> On 02/04/2017 09:19 AM, Ran Shalit wrote: >>> Hello, >>> >>> It is said in documentation: >>> >>> "The key issue is with the number of CPU cores actually running >>> real-time threads and receiving interrupts from real-time sources, not >>> with the overall number of cores on line on the target hardware. >>> Because the Cobalt co-kernel does not share any lock with the regular >>> Linux kernel when dealing with real-time activities, a 16-way server >>> pinning such activities on not more than four of the available cores >>> would still deliver good performances in a Cobalt-based dual kernel >>> configuration." >>> >>> We plan to use xenomai, >>> but the cpu (Atom) is only a single core. >>> >>> Can a single core still gives good results with xenomai ? >>> >> >> Yes. There is nothing in the excerpt above which might suggest the >> opposite btw. >> > > Hi, > > Do you think it is correct to assume that adding cores will result in > a (probably) smaller latency ?
No, it is actually the exact opposite. Adding cores will involve more cache-related latencies, and also require additional serialization for accessing some critical resources. -- Philippe. _______________________________________________ Xenomai mailing list [email protected] https://xenomai.org/mailman/listinfo/xenomai
