Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

> PTP packets with 5 milliseconds of randomness in the scheduling

This should not matter, unless you are a 5G telecom operator running at a high frequency. Gaussian noise in the master is not important to PTP. Being a master is easier than being a slave.

If you are running PTP at 128 Hz like a telecom, delays that large might lead to slaves resetting their state machines, which would blow the whole thing up.

> The CPU can ask the NIC how many nanoseconds ago that was

The CPU can indeed ask the NIC what time it is, but then the CPU has to estimate how long ago the NIC answered the question. If the PCI bus is in L1, it will take 10s to 100s of microseconds (no hard upper bound; could be forever) to train up to L0. The host has to determine this delay and compensate for it, because PCI bus transition is much longer than the desired error in PTP. The easiest way is to repeatedly read the time, discard the outliers, and divide the estimated delay in half. This technique is used by various realtime ethernet stacks. You will note that this is effectively the same as disabling ASPM. This is also why they invented PCIe 3.0 PTM.





> You will note that this is effectively the same as disabling ASPM

You need to wake everything up for certain measurements, but you don't need to disable power saving wholesale.




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: