Alternating Delayed Ping Times

[jhigham]

A few days after the server has been restarted I get alternating delayed ping responses. It will alternate between < one millisecond and about two seconds. Consistently flipping back and forth. This is both with the Intel NICs on the motherboard and the Intel NIC on a card. Both displaying the same behavior. This issue exited some time ago and for the past several months/upgrades it has been fine. It appears to be related/restarted with the last few recent firmware upgrades. I have been consistently keeping the box up to date with most recent stable firmware. Needless to say this results in very poor file transfer speeds until restarted. After a restart server runs fine and in a few days it goes back to same odd network behavior. Removing the NIC card does not change behavior.
Motherboard is Supermicro X8STI-F.
Thank you.

 

[dlavigne]

Were you able to figure this out? If not, what is the driver name for the NICs (from ifconfig)?

 

[jhigham]

Thank you for assisting. Problem still exists, consistently.

Here is the return from ifconfig:

em0: flags=8943<UP,BROADCAST,RUNNING,PROMISC,SIMPLEX,MULTICAST> metric 0 mtu 150
0
options=42098<VLAN_MTU,VLAN_HWTAGGING,VLAN_HWCSUM,WOL_MAGIC,VLAN_HWTSO>
ether 00:25:90:26:50:ec
inet 172.21.0.21 netmask 0xffff0000 broadcast 172.21.255.255
nd6 options=9<PERFORMNUD,IFDISABLED>
media: Ethernet autoselect (1000baseT <full-duplex>)
status: active
em1: flags=8c02<BROADCAST,OACTIVE,SIMPLEX,MULTICAST> metric 0 mtu 1500
options=4219b<RXCSUM,TXCSUM,VLAN_MTU,VLAN_HWTAGGING,VLAN_HWCSUM,TSO4,WOL
_MAGIC,VLAN_HWTSO>
ether 00:25:90:26:50:ed
nd6 options=9<PERFORMNUD,IFDISABLED>
media: Ethernet autoselect
status: no carrier
em2: flags=8843<UP,BROADCAST,RUNNING,SIMPLEX,MULTICAST> metric 0 mtu 1500
options=9b<RXCSUM,TXCSUM,VLAN_MTU,VLAN_HWTAGGING,VLAN_HWCSUM>
ether 00:04:23:d7:c5:31
inet 172.21.251.223 netmask 0xffff0000 broadcast 172.21.255.255
nd6 options=9<PERFORMNUD,IFDISABLED>
media: Ethernet autoselect (1000baseT <full-duplex>)
status: active
ipfw0: flags=8801<UP,SIMPLEX,MULTICAST> metric 0 mtu 65536
nd6 options=9<PERFORMNUD,IFDISABLED>
lo0: flags=8049<UP,LOOPBACK,RUNNING,MULTICAST> metric 0 mtu 16384
options=600003<RXCSUM,TXCSUM,RXCSUM_IPV6,TXCSUM_IPV6>
inet6 ::1 prefixlen 128
inet6 fe80::1%lo0 prefixlen 64 scopeid 0xd
inet 127.0.0.1 netmask 0xff000000
nd6 options=21<PERFORMNUD,AUTO_LINKLOCAL>
bridge0: flags=8843<UP,BROADCAST,RUNNING,SIMPLEX,MULTICAST> metric 0 mtu 1500
ether 02:dc:1a:e9:c8:00
nd6 options=1<PERFORMNUD>
id 00:00:00:00:00:00 priority 32768 hellotime 2 fwddelay 15
maxage 20 holdcnt 6 proto rstp maxaddr 2000 timeout 1200
root id 00:00:00:00:00:00 priority 32768 ifcost 0 port 0
member: epair0a flags=143<LEARNING,DISCOVER,AUTOEDGE,AUTOPTP>
ifmaxaddr 0 port 15 priority 128 path cost 2000
member: em0 flags=143<LEARNING,DISCOVER,AUTOEDGE,AUTOPTP>
ifmaxaddr 0 port 1 priority 128 path cost 20000
epair0a: flags=8943<UP,BROADCAST,RUNNING,PROMISC,SIMPLEX,MULTICAST> metric 0 mtu
1500
options=8<VLAN_MTU>
ether 02:c5:33:00:0f:0a
nd6 options=1<PERFORMNUD>
media: Ethernet 10Gbase-T (10Gbase-T <full-duplex>)
status: active

 

[depasseg]

em0 and em2 are configured to be part of the same broadcast domain. Is that the intended behavior? Seems like they should be configured separately. Check out the Subnet masks and the broadcast IP addresses.

 

[jhigham]

I only have one active at a given time. em0 is the default that I normally run on and I was disconnecting em0 and connecting em2 to see if the delayed pings continue. They did. I also have tried with the card (em2) removed. Same results.

 

[depasseg]

In the ifconfig above, they are both listed as active. Try deleting the em2 interface configuration.

 

[jhigham]

You are correct, I did have the network cable plugged in when I posted that. I'll delete and see if it makes a difference. Thanks for talking a look at this for me.

 

[jhigham]

em2 deleted. Problem still returns/exists. Possibly triggered by high network use?

 

[dlavigne]

If so, there would be errors in /var/log/messages.

 

[jhigham]

This appears to be related to an IPMI issue. Downloaded most recent IPMI from Supermicro and flashed board. Seems OK so far, will keep monitoring.

 

[jhigham]

Not solved. Problem still exists/returns. Generating following error:
ipmi0: KCS: Reply address mismatch
ipmi0: KCS error: 01

 

[cyberjock]

Can you post a debug file from System -> Advanced -> Save Debug?

 

[jhigham]

It has been over a week and no issues. Solution - Disable BMC/IPMI via jumper on motherboard. There is a scary warning in the manual: "JBMC1 is reserved for internal testing only. Do not change the jumper setting pre-set by the manufacturer." No issue changing jumper.

 

[Nick2253]

I'd file a bug report with SuperMicro. You shouldn't have to disable IPMI to fix something like this.