[rrg] [GROW] Operational experience with cache based mapping ID

[Luigi Iannone]

Hi,

the paper http://inl.info.ucl.ac.be/publications/cost-caching-locatorid
shows some basic stats specific to the LISP cache.

If you are interested we can propose other measurements using the 
metrics that Dimitri is listing below (section 3 of the proposed toc).

I think this will be useful to deepen the understanding of the cache 
behavior in LISP, but also more generally on map-and-encaps solutions.

Cheers

Luigi


PAPADIMITRIOU Dimitri wrote:
> Peter,
> 
> the below is what I proposed to Bill that launched the thread: 
> 
> ---
> Section 1: Introduction
> 
> Section 2: Motivations and Roles
> 
> Section 3: Caching Techniques
> 
> Section 3.1: Metrics
> - Hit rate
> - Hit time/Latency
> - Others
> 
> Section 3.2: Cache Replacement Algorithms 
> - Least Recently Used (LRU)
> - Least Recently Replaced (LRR)
> - Least Frequently Used (LFU)
> 
> -> Associativity (Direct mapping, Fully/N-Way/Skewed)
> 
> Section 3.4: Acquisition Techniques 
> - Push: e.g. BGP
> - Pull: e.g. DNS
> - Hybrid Push-Pull 
> 
> Section 4: Operational experience
> 
> - Structure to be refined per input
> 
> Section 5: Conclusions
> 
> ---
> 
> comments are welcome.
> 
> thanks,
> -dimitri.
> 
>> -----Original Message-----
>> From: grow-bounces at ietf.org [mailto:grow-bounces at ietf.org] On 
>> Behalf Of Peter Schoenmaker
>> Sent: Friday, December 19, 2008 12:47 AM
>> To: Ron Bonica
>> Cc: grow at ietf.org; Routing Research Group Mailing List
>> Subject: Re: [GROW] Operational experience with cache based mapping ID
>>
>> Hi,
>>
>> It seems there is interest in this topic.  But to move 
>> forward we need  
>> volunteer(s) to act as the editor.
>>
>> We already have one study 
>> <http://inl.info.ucl.ac.be/publications/cost-caching-locatorid
> -mappings 
>>  > specifically on LISP.  There is a request for a study of existing  
>> deployed protocols that use caching, and their operational impacts.
>>
>> Do we have more specifics about the protocols to be studied, 
>> and what  
>> the paper would contain?
>>
>> peter
>>
>>
>>
>> On Nov 24, 2008, at 11:59 AM, Ron Bonica wrote:
>>
>>> Hi Bill,
>>>
>>> Since we are discussing operational experience, I would 
>> like to see  
>>> the
>>> conversation continue on the GROW list.
>>>
>>> GROW chairs,
>>>
>>> There seems to be interest in this topic. Could you guys appoint a
>>> document editor?
>>>
>>>                                 Ron
>>>
>>>
>>> William Herrin wrote:
>>>> Thanks folks. The question was asked in GROW but it seems like its
>>>> most directly relevant to the research being done in RRG. 
>> I suggest  
>>>> we
>>>> move the discussion to one list or the other and 
>> periodically give an
>>>> update to both. Does anyone have a preference for which list?
>>>>
>>>> Regards,
>>>> Bill
>>>>
>>>>
>>>> On Wed, Nov 19, 2008 at 11:10 AM, PAPADIMITRIOU Dimitri
>>>> <Dimitri.Papadimitriou at alcatel-lucent.be> wrote:
>>>>> i see value in such effort. ready to help.
>>>>> -d.
>>>>>
>>>>>> -----Original Message-----
>>>>>> From: grow-bounces at ietf.org [mailto:grow-bounces at ietf.org] On
>>>>>> Behalf Of William Herrin
>>>>>> Sent: Wednesday, November 19, 2008 5:17 PM
>>>>>> To: grow at ietf.org; Routing Research Group Mailing List
>>>>>> Subject: [GROW] Operational experience with cache based 
>> mapping ID
>>>>>> Hi folks,
>>>>>>
>>>>>> There was a suggestion at grow this morning that we 
>> produce a ID on
>>>>>> operational experience with cache-based mapping systems. 
>> Systems  
>>>>>> like
>>>>>> the DNS have been very successful. On the other hand, I still  
>>>>>> remember
>>>>>> worms sending to random destinations on a 56k modem 
>> DOSing a Cisco
>>>>>> 2500 because of the route cache. It would be very helpful to  
>>>>>> determine
>>>>>> what factors allow a caching strategy to be successful and what
>>>>>> factors tend to lead to failure.
>>>>>>
>>>>>> I think this is very relevant to a number of the solution  
>>>>>> strategies
>>>>>> under discussion on RRG, not just LISP. So, is anyone else  
>>>>>> interested
>>>>>> in organizing the effort? If not, I volunteer.
>>>>>>
>>>>>> Regards,
>>>>>> Bill Herrin
>>>>>>
>>>>>>
>>>>>> --
>>>>>> William D. Herrin ................ herrin at dirtside.com  
>> bill at herrin.us
>>>>>> 3005 Crane Dr. ...................... Web: 
>> <http://bill.herrin.us/>
>>>>>> Falls Church, VA 22042-3004
>>>>>> _______________________________________________
>>>>>> GROW mailing list
>>>>>> GROW at ietf.org
>>>>>> https://www.ietf.org/mailman/listinfo/grow
>>>>>>
>>>>
>>>>
>>> _______________________________________________
>>> GROW mailing list
>>> GROW at ietf.org
>>> https://www.ietf.org/mailman/listinfo/grow
>> _______________________________________________
>> GROW mailing list
>> GROW at ietf.org
>> https://www.ietf.org/mailman/listinfo/grow
>>
> _______________________________________________
> rrg mailing list
> rrg at irtf.org
> https://www.irtf.org/mailman/listinfo/rrg