Steve Bertrand wrote:
Hey all,

I'm experiencing conflicting information on throughput numbers when
comparing information garnered via MRTG on a 1000Mbps HP Procurve, and
netstat -h -w1 on a server connected to the switch.

What I want to know is if netstat in the below case is actually
displaying the info in bits, even though it is telling me the result is
in bytes:

amanda# netstat -h -w1
            input        (Total)           output
   packets  errs      bytes    packets  errs      bytes colls
      109K     0        90M        200     0        14K     0
      104K     0        88M        201     0        14K     0
^C

On a different server running MRTG (FBSD 7.0-STABLE), I have configured
it to display in bits/s, and it is showing ~90Mbps.

Which one is accurate? I'm trying to evaluate the difference between
Cisco Cat 29xx 100Mb switches and this ProCurve GigE 2848 switch. So
far, my results are that the 100Mb Cisco can peak and sustain a 98Mbps
throughput.

The Procurve, unless MRTG is wrong, and netstat output should be 90M*8,
I'm far less than impressed.

...or could it be that MRTG is broken/capped at ~100Mbps calculations?

Thanks for any insight,

If you are using MRTG with SNMP info from switch, be aware of 32 bit counters. If you have high network load on the switch, the counter overflows between two five minutes intervals of MRTG and then MRTG shows inacurate results. (for example 60Mbps instead of 250Mbps peak)

Some devices have 64 bit counters and MRTG can be configured to use these.

netstat is in bytes AFAIK.

Miroslav Lachman
_______________________________________________
[email protected] mailing list
http://lists.freebsd.org/mailman/listinfo/freebsd-net
To unsubscribe, send any mail to "[EMAIL PROTECTED]"

Reply via email to