1

I see the following message repeat every 18-19 minutes on syslog on one of my 2 servers running Centos 7:

kernel: igb 0000:03:00.1: unexpected SYS WRAP

The NIC in question is I350 Gigabit built-in on a Supermicro server. It has 1 port dedicated to running PTP4Linux and one port providing the host's main connection. The server that's experiencing the issue runs Centos 7.3 (1611), and the one that isn't experiencing it still runs Centos 7.1. Any ideas?

Isac Casapu
  • 235
  • 1
  • 11

1 Answers1

2

Looks like the older igb drivers had some issues when setting Time Sync Interrupt Cause Register. From in-kernel Support mailing list and kernel git:

TSAUXC.DisableSystime is never set, so SYSTIM runs into a SYS WRAP every 1100 secs on 80580/i350/i354 (40 bit SYSTIM) and every 35000 secs on 80576 (45 bit SYSTIM).

This wrap event sets the TSICR.SysWrap bit unconditionally.

However, checking TSIM at interrupt time shows that this event does not actually cause the interrupt. Rather, it's just bycatch while the actual interrupt is caused by, for instance, TSICR.TXTS.

The conclusion is that the SYS WRAP is actually expected, so the "unexpected SYS WRAP" message is entirely bogus and just helps to confuse users. Drop it.

So, seems that it's safe to ignore.

Kernel starting from 4.14 and CentOS 7.5 should be free from it

dbrdbr
  • 36
  • 3