All things related to multicast

[Bill Nickless <>]

-----BEGIN PGP SIGNED MESSAGE-----

At 02:47 PM 1/18/2001 +1100, Markus Buchhorn wrote:

>Is it really the *rate* of SA's that is a problem? Or the total number of
>SA's? The issue seemed to be cpuhogging when the routers had 50k SA state
>to deal with under the pressure of a normal background multicast flow.
>Would it perhaps be better to limit the size of the total SA state? I
>wonder what would happen if the 50k SA state has been slowly built up (over
>days, rather than minutes).
>
>Just wondering aloud, no experience or evidence :-)

Very good question.

I would tend to suspect the number of SAs in the table as being the problem.

Remember, each SA has a timer associated with it.  Periodically the MSDP 
process in the router has to run through the table and expire SAs whose 
timers have expired.  I would guess that the MSDP run-through-the-table 
code was taking more CPU than normal, triggering the CPUHOG message.

Sigh.  I really do need to set up a test network to see where the MSDP 
scaling problems actually start showing up.  . o O ( Time: The Final Frontier 
)

(Note: the question of CPU cost to scan the MSDP SA table periodically 
should be considered separately from the cost to actually forward multicast 
packets, because multicast forwarding can [and should] be done in dedicated 
forwarding hardware.)
===
Bill Nickless    http://www.mcs.anl.gov/people/nickless      +1 630 252 7390
PGP:0E 0F 16 80 C5 B1 69 52 E1 44 1A A5 0E 1B 74 F7     


-----BEGIN PGP SIGNATURE-----
Version: PGPfreeware 6.5.8 for non-commercial use <http://www.pgp.com>

iQCVAwUBOmZrsqwgm7ipJDXBAQGDBgP/faL1fBskKggFi9x5Tg/lbIR0SA5Uyt/C
Q2bZQxzmkJVJZfXb3jxpLyt4ac+hslywHpCYfBXIlGruITDJXf4tj0pDZWF9vgLv
EQWLdynFtzoMnmJdtamI4WvHiTxzjsh6ppq7JHaxfmtiZ4Se85nskk7vkW2scpH0
/raqwEKAs2Q=
=yNuz
-----END PGP SIGNATURE-----