Probably due to the test tool you're using. Does the tool serialize the
UDP stream (ie: wait for a response for each packet)?
As far as I understand, not it doesn't. The tool is nepim, version 0.17.
BTW, this should go on freebsd-net.
OK, next time it will.
Thanks!
--
rea
BOFH excuse
Good day!
I've obtained the following strang results with the em Ethernet interface
speeds on a 6.1-PRERELEASE:
Polling on:
UDP stream to FreeBSD: 327843.84 Kbit/sec,
TCP stream to FreeBSD: 524550.12 Kbit/sec.
Polling off:
UDP stream to FreeBSD: 740409.38 Kbit/sec,
TCP stream to
FreeLSD wrote:
Good day!
I've obtained the following strang results with the em Ethernet interface
speeds on a 6.1-PRERELEASE:
Polling on:
UDP stream to FreeBSD: 327843.84 Kbit/sec,
TCP stream to FreeBSD: 524550.12 Kbit/sec.
Polling off:
UDP stream to FreeBSD: 740409.38
On Tue, 21 Feb 2006, FreeLSD wrote:
options SCHED_ULE
I'd start by going back to SCHED_4BSD and seeing how that affects things.
ULE is an experimental scheduler that may produce inconsistent or undesirable
results depending on workload.
Robert N M Watson
On Tue, 21 Feb 2006 19:54:56 +0300, in sentex.lists.freebsd.hackers
you wrote:
Good day!
I've obtained the following strang results with the em Ethernet interface
speeds on a 6.1-PRERELEASE:
Polling on:
UDP stream to FreeBSD: 327843.84 Kbit/sec,
TCP stream to FreeBSD: 524550.12 Kbit/sec.
I'd start by going back to SCHED_4BSD and seeing how that affects things. ULE
is an experimental scheduler that may produce inconsistent or undesirable
results depending on workload.
OK, I will. And I'll follow your next advice about the tcp_inflight and Mike's
advice.
Following Nate
6 matches
Mail list logo