Re: [alto] 'Link capacity' in scope?

2009-06-04 Thread Jan Seedorf
Dear Salman, > In addition to provisioned link capacity, it is useful for end points > to > determine how much of their upload/download quota has been consumed > (assuming ISPs that have a montly bandwidth cap). Like provisioned link > capacity, this information is *indirectly* used by the peers t

Re: [alto] 'Link capacity' in scope?

2009-06-04 Thread Salman Abdul Baset
On Thu, 4 Jun 2009, Enrico Marocco wrote: You are probably thinking a centralized ALTO server. There is no reason why peers cannot act as ALTO servers which inturn obtain their link capacity information from ISP managed ALTO servers. Uh? I'm thinking of a protocol clients can use to query serv

Re: [alto] 'Link capacity' in scope?

2009-06-04 Thread Salman Abdul Baset
On Thu, 4 Jun 2009, Lars Eggert wrote: On 2009-6-3, at 21:14, Salman Abdul Baset wrote: Your congestion example is spot on. Provisioned link capacity (upstream and downstream) is not very helpful for peer selection unless the current load on the link is considered. Agreed, but I understood th

Re: [alto] 'Link capacity' in scope?

2009-06-04 Thread John Leslie
Lars Eggert wrote: > On 2009-6-4, at 10:20, Enrico Marocco wrote: > >> It seems reasonable to allow the ALTO protocol to carry, in addition >> to topology and cost-related information, also other information like >> minimum and perhaps estimated latency (I'll let others argue whether >> both wo

Re: [alto] 'Link capacity' in scope?

2009-06-04 Thread Lars Eggert
On 2009-6-4, at 10:20, Enrico Marocco wrote: It seems reasonable to allow the ALTO protocol to carry, in addition to topology and cost-related information, also other information like minimum and perhaps estimated latency (I'll let others argue whether both would be feasible or not) about the t

Re: [alto] 'Link capacity' in scope?

2009-06-04 Thread Enrico Marocco
John Leslie wrote: >> If we were to design a protocol that "asks" the gateway about current >> status, and the gateway reports that the P2P app can "go for it" with >> respect to available bandwidth, it's possible that a voice call from a >> SIP endpoint somewhere on the home network may star

Re: [alto] 'Link capacity' in scope?

2009-06-04 Thread Enrico Marocco
Salman Abdul Baset wrote: > Nodes (clients) can use the spare capacity (provisioned - current load) of > relay candidates as a metric to guide their search of relays. I think > such a usage is peer selection optimization. What do you think? Ok, I'm totally lost now. I thought your

Re: [alto] 'Link capacity' in scope?

2009-06-04 Thread Lars Eggert
On 2009-6-3, at 22:11, Salman Abdul Baset wrote: Nevertheless, it is not impossible to use the number of [TCP] bits sent and received from a machine on which an ALTO enabled application is running to gauge current load. Yes, this is not a precise number but is reasonable enough to be useful

Re: [alto] 'Link capacity' in scope?

2009-06-04 Thread Lars Eggert
On 2009-6-3, at 21:14, Salman Abdul Baset wrote: Your congestion example is spot on. Provisioned link capacity (upstream and downstream) is not very helpful for peer selection unless the current load on the link is considered. Agreed, but I understood that that was the information you were