[Bug 225918] msk: excessive latency on arm64

[bugzilla-noreply at freebsd.org]

https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=225918

            Bug ID: 225918
           Summary: msk: excessive latency on arm64
           Product: Base System
           Version: CURRENT
          Hardware: Any
                OS: Any
            Status: New
          Severity: Affects Only Me
          Priority: ---
         Component: kern
          Assignee: freebsd-bugs at FreeBSD.org
          Reporter: emaste at freebsd.org

More details to come - PR submitted to track working/failing revisions/dates.
Observed on my Softiron Overdrive 1000, running a kernel from r329060:

root at od1000:~ # ping 192.168.11.1
PING 192.168.11.1 (192.168.11.1): 56 data bytes
64 bytes from 192.168.11.1: icmp_seq=0 ttl=64 time=297.339 ms
64 bytes from 192.168.11.1: icmp_seq=1 ttl=64 time=314.382 ms
64 bytes from 192.168.11.1: icmp_seq=2 ttl=64 time=303.234 ms
64 bytes from 192.168.11.1: icmp_seq=3 ttl=64 time=356.380 ms
64 bytes from 192.168.11.1: icmp_seq=4 ttl=64 time=379.047 ms
64 bytes from 192.168.11.1: icmp_seq=5 ttl=64 time=402.130 ms
64 bytes from 192.168.11.1: icmp_seq=6 ttl=64 time=464.899 ms
64 bytes from 192.168.11.1: icmp_seq=7 ttl=64 time=493.329 ms
64 bytes from 192.168.11.1: icmp_seq=8 ttl=64 time=537.635 ms
64 bytes from 192.168.11.1: icmp_seq=9 ttl=64 time=570.663 ms
64 bytes from 192.168.11.1: icmp_seq=10 ttl=64 time=621.863 ms
64 bytes from 192.168.11.1: icmp_seq=11 ttl=64 time=660.115 ms
64 bytes from 192.168.11.1: icmp_seq=12 ttl=64 time=701.733 ms
64 bytes from 192.168.11.1: icmp_seq=13 ttl=64 time=744.956 ms
64 bytes from 192.168.11.1: icmp_seq=14 ttl=64 time=791.934 ms
64 bytes from 192.168.11.1: icmp_seq=15 ttl=64 time=845.377 ms
64 bytes from 192.168.11.1: icmp_seq=16 ttl=64 time=898.613 ms
64 bytes from 192.168.11.1: icmp_seq=17 ttl=64 time=954.177 ms
64 bytes from 192.168.11.1: icmp_seq=18 ttl=64 time=1014.196 ms
64 bytes from 192.168.11.1: icmp_seq=19 ttl=64 time=1056.473 ms
64 bytes from 192.168.11.1: icmp_seq=20 ttl=64 time=1059.959 ms
64 bytes from 192.168.11.1: icmp_seq=21 ttl=64 time=1062.538 ms
64 bytes from 192.168.11.1: icmp_seq=22 ttl=64 time=1062.954 ms
64 bytes from 192.168.11.1: icmp_seq=23 ttl=64 time=1052.935 ms
64 bytes from 192.168.11.1: icmp_seq=24 ttl=64 time=1064.865 ms
64 bytes from 192.168.11.1: icmp_seq=25 ttl=64 time=1056.929 ms
64 bytes from 192.168.11.1: icmp_seq=26 ttl=64 time=1062.470 ms
^C
--- 192.168.11.1 ping statistics ---
28 packets transmitted, 27 packets received, 3.6% packet loss
round-trip min/avg/max/stddev = 297.339/734.486/1064.865/283.196 ms

cognet@ reports a Dec 3 kernel worked.

Feb 15 09:38:17 od1000 kernel: mskc0: <Marvell Yukon 88E8059 Gigabit Ethernet>
port 0x1000-0x10ff mem 0x40000000-0x40003fff at device 0.0 on pci2
Feb 15 09:38:17 od1000 kernel: msk0: <Marvell Technology Group Ltd. Yukon
Optima Id 0xbc Rev 0x01> on mskc0
Feb 15 09:38:17 od1000 kernel: msk0: Using defaults for TSO: 65518/35/2048
Feb 15 09:38:17 od1000 kernel: msk0: Ethernet address: <elided>
Feb 15 09:38:17 od1000 kernel: miibus0: <MII bus> on msk0
Feb 15 09:38:17 od1000 kernel: e1000phy0: <Marvell PHYG65G Gigabit PHY> PHY 0
on miibus0
Feb 15 09:38:17 od1000 kernel: e1000phy0:  none, 10baseT, 10baseT-FDX,
100baseTX, 100baseTX-FDX, 1000baseT, 1000baseT-master, 1000baseT-FDX,
1000baseT-FDX-master, auto, auto-flow

-- 
You are receiving this mail because:
You are the assignee for the bug.