[nsp] SUP1-MSFC performance?

Tim Stevenson tstevens at cisco.com
Wed Feb 11 18:12:04 EST 2004

Expense, board space, and technical reasons/tradeoffs are what limit the size.

We don't use TCAM for the NF table in sup1/sup2, we are using SRAMs. Sup720 uses a TCAM for storing the NF hash results, which allows for better efficiency/utilization, but we still use SRAM for the entries themselves.

If you need more NF table space, consider sup720 (128K max/96K util) or sup720-3bxl (256K max/230K util).


At 03:04 PM 2/11/2004, cisco-nsp-request at puck.nether.net proclaimed:
>Date: Thu, 12 Feb 2004 00:45:01 +0200
>From: Konstantin Barinov <sbr at infonet.ee>
>Subject: Re[2]: [nsp] SUP1-MSFC performance?
>To: cisco-nsp at puck.nether.net
>Message-ID: <268389538.20040212004501 at infonet.ee>
>Content-Type: text/plain; charset=us-ascii
>>>TS> The NF table is 128K max entries, 32K average, based on the
>>>TS> efficiency of the hash. YMMV. Hash collisions result in software
>>>TS> CEF switching.
>>>btw, I was always interested, why NF table is limited to 128K entries?
>AF> Because TCAM is expensive?
>How expensive comparing to cat 6500 switch? ;)

Tim Stevenson, tstevens at cisco.com
Routing & Switching CCIE #5561
Technical Marketing Engineer, Catalyst 6500
Cisco Systems, http://www.cisco.com
IP Phone: 408-526-6759
The contents of this message may be *Cisco Confidential*
and are intended for the specified recipients only.

More information about the cisco-nsp mailing list