Messages in this thread | | | Date | Thu, 23 Sep 2010 22:34:17 +0100 | From | Alan Cox <> | Subject | Re: [PATCH v6 0/8] ptp: IEEE 1588 hardware clock support |
| |
> There is no other scalable time source available for fast timer access > than the time stamp counter in the cpu. Other time source require > memory accesses which is inherently slower.
On what hardware ?
> An accurate other time source is used to adjust this clock. NTP does that > via the clock interfaces from user space which has its problems with > accuracy. PTP can provide the network synced time access > that would a more accurate calibration of the time.
Accuracy does not require speed of access. Accuracy requires predictible latency of access.
> Userland code would introduce latencies that would make sub microsecond > time sync very difficult.
You can take a multiple micro-second I/O stall or SMI trap on a PC so you already lost the battle on the platform you seem to be discussing.
> You dont need the user APIs if you directly use the PTP time source to > steer the system clock. In fact I think you have to do it in kernel space > since user space latencies will degrade accuracy otherwise.
PTP is not a 'time source' it is one or more source of time. The distinction is rather important.
> It implies clock tuning in userspace for a potential sub microsecond > accurate clock. The clock accuracy will be limited by user space > latencies and noise. You wont be able to discipline the system clock > accurately.
Noise matters, latency doesn't. And the kernel is getting more and more real time support all the time.
| |