|
On Mon, 24 Jan 2000, Joseph Mack wrote:
> I am beginning to think
> that netpipe may not be a good test - each window is sending its packet
> and measuring the throughput for its packet. If because of contention for
> resources, a netpipe process has to wait before starting to send a packet
> and this wait is not included in the timing, then the measured throughput
> will be higher than the real throughput. I will write to the netpipe
> person and ask about this.
Just got a reply from the netpipe maintainer. Since my netpipe processes
are not synchronised and the best result is reported for replicated
packets, in principle I could get 6x100Mbps when testing with 6
realservers. There is a test version of a clustered netpipe (multiple
servers are tested in synchrony) which the maintainer will send to
me to try.
Joe
--
Joseph Mack mack@xxxxxxxxxxx
----------------------------------------------------------------------
LinuxVirtualServer.org mailing list - lvs-users@xxxxxxxxxxxxxxxxxxxxxx
To unsubscribe, e-mail: lvs-users-unsubscribe@xxxxxxxxxxxxxxxxxxxxxx
For additional commands, e-mail: lvs-users-help@xxxxxxxxxxxxxxxxxxxxxx
|
