Sorry folks,
Was meant for juniper-nsp
adam
>
Adam Vitkovsky
IP Engineer
T: 0333 006 5936
E: [email protected]
W: www.gamma.co.uk
This is an email from Gamma Telecom Ltd, trading as “Gamma”. The contents of
this email are confidential to the ordinary user of the email address to which
it was addressed. This email is not intended to create any legal relationship.
No one else may place any reliance upon it, or copy or forward all or any of it
in any form (unless otherwise notified). If you receive this email in error,
please accept our apologies, we would be obliged if you would telephone our
postmaster on +44 (0) 808 178 9652 or email [email protected]
Gamma Telecom Limited, a company incorporated in England and Wales, with
limited liability, with registered number 04340834, and whose registered office
is at 5 Fleet Place London EC4M 7RD and whose principal place of business is at
Kings House, Kings Road West, Newbury, Berkshire, RG14 5BY.
-----Original Message-----
> From: cisco-nsp [mailto:[email protected]] On Behalf Of
> Adam Vitkovsky
> Sent: 21 September 2015 13:24
> To: [email protected]
> Subject: [c-nsp] FBF vs default route
>
> Hi Saku, all,
>
> In order to route traffic to internet VRF one can use either default route
> pointing at Internet VRF or FBF to dictate which table will be used to perform
> the lookup.
> Each of these comes with a certain performance tax and I’d like to figure out
> which method would be faster two lookups or FBF and one lookup?
>
> Reading the TRIO papers the lookup “workflow” consists of all the features
> enabled and the complexity of the workflow dictates how many lookups into
> RLDRAM are necessary. And I believe that the overall lookup performance
> basically boils down to how many memory lookups are needed per
> workflow.
>
> It could be that the queries to RLDRAM are bundled while the workflow is in
> progress and at the end the RLDRAM is queried only once maybe even in a
> parallel fashion(remember there are 4 phy mem blocks), to retrieve all the
> info needed to modify the packet header or yield the egress LC.
>
> However this can't be done if the workflow requires some information from
> RLDRAM in order to complete, in that case RLDRAM would have to be
> accessed multiple times during the workflow waiting for data to be retrieved
> from RLDRAM and that would increase the lookup time significantly.
>
> I'd like to understand the lookup performance vs. functionality trade-off on
> TRIO chipset and I wasn't able to find any info unfortunately.
>
>
>
>
> adam
>
>
> Adam Vitkovsky
> IP Engineer
>
> T: 0333 006 5936
> E: [email protected]
> W: www.gamma.co.uk
>
> This is an email from Gamma Telecom Ltd, trading as “Gamma”. The contents
> of this email are confidential to the ordinary user of the email address to
> which it was addressed. This email is not intended to create any legal
> relationship. No one else may place any reliance upon it, or copy or forward
> all or any of it in any form (unless otherwise notified). If you receive this
> email in error, please accept our apologies, we would be obliged if you would
> telephone our postmaster on +44 (0) 808 178 9652 or email
> [email protected]
>
> Gamma Telecom Limited, a company incorporated in England and Wales,
> with limited liability, with registered number 04340834, and whose registered
> office is at 5 Fleet Place London EC4M 7RD and whose principal place of
> business is at Kings House, Kings Road West, Newbury, Berkshire, RG14 5BY.
>
>
> _______________________________________________
> cisco-nsp mailing list [email protected]
> https://puck.nether.net/mailman/listinfo/cisco-nsp
> archive at http://puck.nether.net/pipermail/cisco-nsp/
_______________________________________________
cisco-nsp mailing list [email protected]
https://puck.nether.net/mailman/listinfo/cisco-nsp
archive at http://puck.nether.net/pipermail/cisco-nsp/
