Hmm, I understand now that the value for /proc/xenomai/latency is for the anticipation algorithm of timers. This anticipation algorithm is responsible for optimizing the minimal jitter time for timers. Is the latency value used also elsewhere in Xenomai ?
If, say, I would use latencies calibrated with user space POSIX timers for a typical work load, what would happen to timers that are running in kernel or interrupt space ? Would they then be too early ? Have negative values any negative effect besides running too early ? In other words: when one uses timers inside Kernel, ISR's and User space at the same time, which value should be used for /proc/xenomai/latency ? Wouldn't it make sense then to have 3 different latency values for the 3 possible environments ? Best regards, Daniel Schnell. -----Original Message----- From: Gilles Chanteperdrix [mailto:[EMAIL PROTECTED] Sent: 3. maí 2007 15:08 To: [EMAIL PROTECTED] Cc: Daniel Schnell; [email protected] Subject: Re: [Xenomai-help] Latency calculation and test Philippe Gerum wrote: > Sidenote: It obviously makes no sense to stuff gigantic values into > /proc/xenomai/latency; large core latencies are likely the sign of > 1) a bug in the arch-dep section (probably Adeos), 2) inadequation of > the hw for real-time usage (e.g. some ARM platforms with MMU, mmm... > issues). Here I disagree: if a platform run ten times slower than another, why not having a latency ten times bigger ? > Said differently, I had no clue, so I'm expecting users to have some. Additionnaly, the latency depends on the kind of load put on the system during the test. A user is expected to calibrate the nucleus latency of his system under the particular load which is expected on his system. We should add a page on the wiki about the latency calibration. -- Gilles Chanteperdrix _______________________________________________ Xenomai-help mailing list [email protected] https://mail.gna.org/listinfo/xenomai-help
