There has been lots of threads about this on the mailing list. The short
of it:
- increased latency !=3D slower !=3D less throughput
- make sure you have turned off all debugging (some of it needs to be
compiled out)
- LERs inherently have a higher latency then normal IP routing (IP lookup
AND label lookup or push) if you have LERs in your test path, it will
have higher latency
- mpls-linux is not optimized for speed, but for flexibility and correctness
- I welcome definitive data that proves LSR throughput is sub-optimal
- I welcome patches that provide a definitive decrease in latency or solve
any sub-optimal throughput if it exists
On Tue, Jun 28, 2005 at 02:56:14PM +0200, Ra?l Gil wrote:
> Hello! I have created this network
>=20
> 192.168.1.1----------LER A----------LSR------------LER B----------192.168=
.4.2
>=20
> and I have tested with command ping. But I have verified who the
> results are worse with mpls than with IP routing. I believe that
> routers takes long time in swap labels.
>=20
> it is normal (it would not have to be)? or my pc's would have to be faste=
r?
>=20
> Ra?l Gil.
>=20
>=20
> -------------------------------------------------------
> SF.Net email is sponsored by: Discover Easy Linux Migration Strategies
> from IBM. Find simple to follow Roadmaps, straightforward articles,
> informative Webcasts and more! Get everything you need to get up to
> speed, fast. http://ads.osdn.com/?ad_idt77&alloc_id=16492&op?k
> _______________________________________________
> mpls-linux-general mailing list
> mpl...@li...
> https://lists.sourceforge.net/lists/listinfo/mpls-linux-general
--=20
James R. Leu
jl...@mi...
|
