Hi Richard, Thanks for you reply, it could indeed be the problem. The problem as described with the included output of linuxptp is every day the same. The time even always jumps ahead 1125899906842XXX nanoseconds. Always exactly the same value except for the last three (few) values of the offset.
Jord > On 25 Jan 2019, at 04:42, Richard Cochran <richardcoch...@gmail.com> wrote: > > On Thu, Jan 24, 2019 at 07:56:10AM -0800, Richard Cochran wrote: >> On Thu, Jan 24, 2019 at 12:53:37PM +0000, Jord Pool wrote: >>> 00:1f.6 Ethernet controller: Intel Corporation Ethernet Connection (2) >>> I219-LM >> >> Assuming the fault comes when running on this port: there are HW >> issues with the i219, IIRC. > > You could try this patch: > > commit e1f65b0d70e9e5c80e15105cd96fa00174d7c436 > Author: Miroslav Lichvar <mlich...@redhat.com> > Date: Tue Oct 23 14:37:39 2018 +0200 > > e1000e: allow non-monotonic SYSTIM readings > > It seems with some NICs supported by the e1000e driver a SYSTIM reading > may occasionally be few microseconds before the previous reading and if > enabled also pass e1000e_sanitize_systim() without reaching the maximum > number of rereads, even if the function is modified to check three > consecutive readings (i.e. it doesn't look like a double read error). > This causes an underflow in the timecounter and the PHC time jumps hours > ahead. > > This was observed on 82574, I217 and I219. The fastest way to reproduce > it is to run a program that continuously calls the PTP_SYS_OFFSET ioctl > on the PHC. > > Modify e1000e_phc_gettime() to use timecounter_cyc2time() instead of > timecounter_read() in order to allow non-monotonic SYSTIM readings and > prevent the PHC from jumping. > > > Thanks, > Richard _______________________________________________ Linuxptp-users mailing list Linuxptp-users@lists.sourceforge.net https://lists.sourceforge.net/lists/listinfo/linuxptp-users
