Multipeer
Provided are methods and systems for creating an optimal set of reflector peers, comprising detecting a plurality of reflector peers, retrieving a plurality of static metrics from each of the plurality of reflector peers, ranking the plurality of reflector peers based on the plurality of static metrics, selecting a top predetermined number of peers from each static metric, establishing the selected reflector peers as the optimal set of reflector peers, determining dynamic metric for each of the plurality of reflector peers, and adjusting the optimal set of reflector peers based on the dynamic metric.
1. A method for creating an optimal set of reflector peers, comprising:
detecting a plurality of reflector peers;
generating a combined metric construction factor for two or more reflector peers of the plurality of reflector peers, wherein generating a combined metric construction factor comprises receiving, for the two or more reflector peers, one or more of a servicing load metric, a link capacity metric, a proximity metric, an Internet Service Provider (ISP) metric, a Network Address Translator (NAT) metric, and a cache correlation metric, and wherein generating a combined metric construction factor comprises normalizing one or more of the servicing load metric, link capacity metric, proximity metric, ISP metric, NAT metric, and cache correlation metric according to V ij ′=V ij /Max j , wherein the value of metric j of peer i is denoted by V ij and Max j is the maximum value of all peers for metric j;
selecting a pre-determined number of reflector peers based on the generated combined metric construction factor; and
establishing the selected reflector peers as the optimal set of reflector peers.
2. The method of claim 1 , wherein generating a combined metric construction factor for each of the plurality of reflector peers comprises performing initial peer assignment on the plurality of reflector peers.
3. The method of claim 2 , wherein performing initial peer assignment on the plurality of reflector peers comprises:
ranking the plurality of reflector peers based on one or more of the servicing load metric, link capacity metric, proximity metric, ISP metric, and NAT metric;
selecting a top predetermined number of peers from each of the one or more metrics; and
establishing the selected reflector peers as the optimal set of reflector peers.
4. The method of claim 1 , wherein retrieving a servicing load metric comprises determining a number of peers served by each peer.
5. The method of claim 1 , wherein retrieving a link capacity metric comprises actively probing to determine a minimum link capacity of two peers away from each peer.
6. The method of claim 1 , wherein retrieving a proximity metric comprises determining an Internet Protocol (IP) address for the two or more reflector peers of the plurality of reflector peers and correlating each IP address with an IP address geo-location database to determine a physical location for the two or more reflector peers of the plurality of reflector peers.
7. The method of claim 1 , wherein retrieving an Internet Service Provider (ISP) metric comprises actively probing to determine a route taken by data packets and extracting ISP information.
8. The method of claim 1 , wherein retrieving a NAT metric comprises:
determining whether each of the two or more reflector peers is behind a NAT device; and
if a peer is behind a NAT device, determining a number of peers behind the NAT device.
9. The method of claim 1 , wherein generating a combined metric construction factor comprises:
applying a weight to each normalized metric value; and
for each of the plurality of reflector peers, adding the weighted normalized metric values associated with that peer.
10. The method of claim 1 , wherein the cache correlation metric is determined based on receipt of one data packet.
11. The method of claim 1 , wherein the cache correlation metric is determined based on a receipt of a plurality of data packets, wherein the cache correlation metric is updated according to Cor cur — i =e*Cor old — i +(1−e)*Cor cur — i , where in Cor cur — i represents a current cache correlation metric, Cor old — i represents a previous cache correlation metric, and e represents a weighting factor, Cor cur — i =1 if a current packet is correlated between two reflector peers, otherwise Cor cur — i =0.
12. The method of claim 1 , wherein the method is periodically repeated.
13. The method of claim 1 , wherein the method is repeated based on the occurrence of a network event.
14. The method of claim 13 , wherein the network event comprises one or more of, network performance levels dropping below a threshold, offline reflector peers, data transmissions occurring primarily between a subset of the set of optimal reflector peers, and network performance levels increasing beyond a threshold.
15. A system for creating an optimal set of reflector peers, comprising:
a plurality of reflector processors, wherein one of the plurality of reflector processors is configured for
detecting a plurality of reflector processors;
generating a combined metric construction factor for two or more reflector processors of the plurality of reflector processors, wherein generating a combined metric construction factor comprises receiving, for the two or more reflector processors, one or more of a servicing load metric, a link capacity metric, a proximity metric, an Internet Service Provider (ISP) metric, a Network Address Translator (NAT) metric, and a cache correlation metric, and wherein generating a combined metric construction factor comprises normalizing one or more of the servicing load metric, link capacity metric, proximity metric, ISP metric, NAT metric, and cache correlation metric according to V ij ′=V ij /Max j , wherein the value of metric j of peer i is denoted by V ij and Max j is the maximum value of all peers for metric j.
selecting a pre-determined number of reflector processors based on the generated combined metric construction factor; and
establishing the selected reflector processors as the optimal set of reflector peers.
16. A system for creating an optimal set of reflector peers, comprising:
a plurality of reflector processors, wherein one of the plurality of reflector processors is configured for
detecting a plurality of reflector processors;
retrieving one or more of a servicing load metric, a link capacity metric, a proximity metric, and an Internet Service Provider (ISP) metric for two or more of the plurality of reflector processors;
determining a cache correlation metric for the two or more of the plurality of reflector processors;
normalizing one or more of the metrics according to V ij ′=V ij /Max j , wherein the value of metric j of peer i is denoted by V ij and Max j is the maximum value of all peers for metric j;
ranking the two or more of the plurality of reflector processors based on one or more of the normalized metrics;
selecting a top predetermined number of processors from each of the one or more metrics; and
establishing the selected reflector processors as the optimal set of reflector peers.
17. A method for creating an optimal set of reflector peers, comprising:
detecting a plurality of reflector peers;
retrieving one or more of a servicing load metric, a link capacity metric, a proximity metric, and an Internet Service Provider (ISP) metric for two or more of the plurality of reflector peers;
determining a cache correlation metric for the two or more of the plurality of reflector peers;
normalizing one or more of the metrics according to V ij ′=V ij /Max j , wherein the value of metric j of peer i is denoted by V ij and Max j is the maximum value of all peers for metric j;
ranking the two or more of the plurality of reflector peers based on one or more of the normalized metrics;
selecting a top predetermined number of peers from each of the one or more metrics; and
establishing the selected reflector peers as the optimal set of reflector peers.
18. The method of claim 17 , wherein retrieving a servicing load metric comprises determining a number of peers served by each peer.
19. The method of claim 17 , wherein retrieving a link capacity metric comprises actively probing to determine a minimum link capacity of two peers away from each peer.
20. The method of claim 17 , wherein retrieving a proximity metric comprises determining an Internet Protocol (IP) address for each the plurality of reflector peers and correlating each IP address with an IP address geo-location database to determine a physical location for each of the plurality of reflector peers.
21. The method of claim 17 , wherein retrieving an Internet Service Provider (ISP) metric comprises actively probing to determine a route taken by data packets and extracting ISP information.
22. The method of claim 17 , wherein the cache correlation metric is determined based on receipt of a plurality of data packets, wherein the cache correlation metric is updated according to Cor cur — i =e*Cor old — i +(1−e)*Cor cur — i , wherein Cor cur — i represents a current cache correlation metric, Cor old — i represents a previous cache correlation metric, and e represents a weighting factor, Cor cur i =1 if a current packet is correlated between two reflector peers, otherwise Cor cur — i =0.
23. The method of claim 17 , further comprising determining a NAT metric and ranking the plurality of reflector peers based on one or more of the servicing load metric, link capacity metric, proximity metric, ISP metric, cache correlation metric, and NAT metric.
24. The method of claim 23 , wherein retrieving a NAT metric for each of the plurality of peers comprises:
determining whether each peer is behind a NAT device; and
if a peer is behind a NAT device, determining a number of peers behind the NAT device.
25. The method of claim 17 , further comprising:
generating a combined metric construction factor for each of the plurality of reflector peers; and
adjusting the optimal set of reflector peers based on the combined metric construction factor.
26. The method of claim 25 , wherein generating a combined metric construction factor for each of the plurality of reflector peers comprises:
applying a weight to each normalized metric value; and
for each of the plurality of reflector peers, adding the weighted normalized metric values associated with that peer.
27. The method of claim 17 , wherein the method is periodically repeated.
28. The method of claim 17 , wherein the method is repeated based on the occurrence of a network event.
29. The method of claim 28 , wherein the network event comprises one or more of, network performance levels dropping below a threshold, offline reflector peers, data transmissions occurring primarily between a subset of the set of optimal reflector peers, and network performance levels increasing beyond a threshold.
30. A system for creating an optimal set of reflector peers, comprising:
a plurality of reflector processors, wherein one of the plurality of reflector processors is configured for
detecting a plurality of reflector processors;
receiving, for two or more reflector processors of the plurality of reflector processors, one or more of a servicing load metric, a link capacity metric, a proximity metric, an Internet Service Provider (ISP) metric, and a Network Address Translator (NAT) metric;
ranking the plurality of reflector processors based on one or more of the servicing load metric, link capacity metric, proximity metric, ISP metric, and NAT metric;
selecting a top predetermined number of processors based on one or more of the metrics;
establishing the selected reflector processors as the optimal set of reflector peers;
determining a cache correlation metric for the two or more reflector processors of the plurality of reflector processors, wherein the cache correlation metric is determined according to Cor cur — i =e*Cor old — i +(1−e)*Cor cur — i , wherein Cor cur — i represents a current cache correlation metric, Cor old — i represents a previous cache correlation metric, and e represents a weighting factor, Cor cur — i =1 if a current packet is correlated between two reflector peers, otherwise Cor cur — i =0; and
adjusting the optimal set of reflector peers based on the cache correlation metric.
31. A method for creating an optimal set of reflector peers, comprising:
detecting a plurality of reflector peers;
receiving, for two or more reflector peers of the plurality of reflector peers, one or more of a servicing load metric, a link capacity metric, a proximity metric, an Internet Service Provider (ISP) metric, and a Network Address Translator (NAT) metric;
ranking the plurality of reflector peers based on one or more of the servicing load metric, link capacity metric, proximity metric, ISP metric, and NAT metric;
selecting a top predetermined number of peers based on one or more of the metrics;
establishing the selected reflector peers as the optimal set of reflector peers;
determining a cache correlation metric for the two or more reflector peers of the plurality of reflector peers, wherein the cache correlation metric is determined according to Cor cur — i =e*Cor old — i +(1−e)*Cor cur — i , wherein Cor cur — i represents a current cache correlation metric, Cor old — i represents a previous cache correlation metric, and e represents a weighting factor, Cor cur — i =1 if a current packet is correlated between two reflector peers, otherwise Cor cur — i =0; and
adjusting the optimal set of reflector peers based on the cache correlation metric.
32. The method of claim 31 , further comprising:
determining a combined metric construction factor for the two or more reflector peers of the plurality of reflector peers based on the servicing load metric, link capacity metric, proximity metric, ISP metric, cache correlation metric, and NAT metric; and
adjusting the optimal set of reflector peers based on the combined metric construction factors.
33. The method of claim 31 , wherein the method is repeated based on the occurrence of a network event.
34. The method of claim 33 , wherein the network event comprises one or more of, network performance levels dropping below a threshold, offline reflector peers, data transmissions occurring primarily between a subset of the set of optimal reflector peers, and network performance levels increasing beyond a threshold.