[SNMP4J] Performance Benchmarks

[Frank Fock]

Hi Adam,

It seems that you have done the test with debugging
enabled in the trap receiver. Have you tried the
same with the "-d OFF" option?

Are you sure that the UDP buffer of the target OS
is big enough to handle 1000 trap packets per
second?

Best regards,
Frank

Adam Brons wrote:
> I am wondering if any performance benchmarks have been done using the 
> SNMP4J API to receive v1 and v2c traps.  We have a test application to 
> send 1000 v1 traps per second to the SNMP4j command-line tool using the 
> following command-line options:
>     SNMP4J -Ol 0.0.0.0/162
> 
> What we have noticed it that over a period of 9 seconds only 1348 v1 traps 
> were processed by the SNMP4j command-line tool.  This works out to 149 
> traps per second.  Does this sound on pair or should I be expecting a 
> great number more or less.
> 
> Adam Brons
> TSOM Software Engineer
> IBM Tivoli Software
> _______________________________________________
> SNMP4J mailing list
> SNMP4J at agentpp.org
> http://lists.agentpp.org/mailman/listinfo/snmp4j

-- 
AGENT++
http://www.agentpp.com
http://www.mibexplorer.com
http://www.mibdesigner.com