Blade switch 3020 problem

[valsidalv]

Hello,

I'm using c7000 with 3 blade servers. In this enclosure I have 2 Cisco Catalyst Blade switches 3020(12.2(44)SE1). These switches are connected to 2 uplink redundant switches.

In blade switches I have default configuration except set up IP addresses.

I discovered strange problem. When I made ping between blade servers and from blades servers to default gateway I got this output.

>ping 10.0.0.101 -t

Pinging 10.0.0.101 with 32 bytes of data:

Reply from 10.0.0.101: bytes=32 time=-9ms TTL=128

Reply from 10.0.0.101: bytes=32 time=-9ms TTL=128

Reply from 10.0.0.101: bytes=32 time=-9ms TTL=128

Reply from 10.0.0.101: bytes=32 time=-9ms TTL=128

Reply from 10.0.0.101: bytes=32 time=-9ms TTL=128

Reply from 10.0.0.101: bytes=32 time=-9ms TTL=128

Reply from 10.0.0.101: bytes=32 time=-9ms TTL=128

Reply from 10.0.0.101: bytes=32 time=-9ms TTL=128

Reply from 10.0.0.101: bytes=32 time=-9ms TTL=128

Reply from 10.0.0.101: bytes=32 time=2ms TTL=128

Ping statistics for 10.0.0.101:

Packets: Sent = 10, Received = 10, Lost = 0 (0% loss),

Approximate round trip times in milli-seconds:

Minimum = 2ms, Maximum = -9ms, Average = 429496721ms

What can cause negative value of ping? Network infrastructure is working, but this output from ping isn't probably very good.

Many thanks,

Vladislav

[didyap]

I think that doesn't mean a negative value for the miliseconds is just a dash for indicate the value

[ian.vaughan]

Hello,

Multi-core CPU's can experience "Time Stamp Counter" (TSC) drift. This drift between the times on the cores throws out the ping timings.

Go to www.hp.com and search for c01075682 - this is a doc that explains what is going on. You should be able to patch the blades to fix the problem. Raise a support case with HP if you get stuck.

Cheers

Ian