edwardthern wrote: > _ > > HERE_IS_SOME_INFO_FROM_REDHAT...[IF_YOU_CAN_BELIEVE_THEY_KNOW_WHAT_THEY_ARE_TALKING_ABOUT]_ > Newer CPUs may alter their performance based on a workload heuristic in > order to save > power. This is at odds with latency-sensitive workload requirements, > causing sub-optimal > performance/jitter. > > here is limited flexibility with regard to kernel threads as > compared to userspace threads. Here are some options for task affinity > and isolation to > reduce jitter and latency:Isolate CPU cores from > userspace tasks > . > > https://access.redhat.com/sites/default/files/attachments/2012_perf_brief-low_latency_tuning_for_rhel6_0.pdf > > > FYI, plenty of more information on the Web. Texas Instruments, RedHat > and plenty of other companies with the money and staff to do "real" > research can provide a lot of good data. All of my tweaks etc. comes > from them as suppose to arm-chair engineers found in forums. > > Years ago I read an article by Texas Instruments which clearly showed > the results of an experiment that showed the correlation between USB > wire length and jitter.....even as USB trace increased on motherboards > jitter increased. Of course as predicted people laughed at me and said I > was crazy....clinging to the idea of some crap about digital data via > spdif needed to be >1.5m and applying that to USB [because it too was > digital data].
The "jitter and latency" referred to in that Redhat article is the delay and variability in scheduling of real-time threads. Nothing at all to do with the jitter of a clock in a DAC. ------------------------------------------------------------------------ utgg's Profile: http://forums.slimdevices.com/member.php?userid=40900 View this thread: http://forums.slimdevices.com/showthread.php?t=106578 _______________________________________________ audiophiles mailing list audiophiles@lists.slimdevices.com http://lists.slimdevices.com/mailman/listinfo/audiophiles
