Adaptation of data centers' bandwidth contribution to distributed streaming operations
First Claim
1. A large scale system, comprising:
- data centers comprising fractional-storage CDN servers, each server configured to store less than a minimum amount of data needed to decode its stored erasure-coded fragments;
assembling devices, each configured to obtain erasure-coded fragments from at least one nonempty subset of the servers, and to measure fragment delivery parameters; and
at least one decision component configured to generally improve the measured parameters by occasional change of at least some of the servers of the subsets associated with some of the assembling devices, wherein the occasional change comprises excluding underperforming servers from the subsets;
the system configured to exclude underperforming data center by monitoring the fragment-delivery bandwidth utilized by the servers of each data center, and to reduce the bandwidth available to the servers of a data center that was found to utilize less than a certain bandwidth level;
wherein the erasure-coding is rateless-coding enabling a redundancy factor greater than four;
the system comprises;
more than ten data centers scattered across a wide geographical area, more than one hundred servers, each configured to store less than one fifth the minimum amount fragments needed to decode the fragments, and more than ten thousand assembling devices located at user premises and configured to obtain the fragments from the servers via the Internet.
4 Assignments
0 Petitions
Accused Products
Abstract
Adaptation of data centers'"'"' bandwidth contribution to distributed streaming operations, including data centers comprising fractional-storage CDN servers storing erasure-coded fragments encoded with a redundancy factor R greater than one, assembling devices obtaining the fragments from subsets of the servers, and measuring fragment delivery parameters, and at least one decision component that occasionally changes at least some of the servers of the subsets to generally improve the measured parameters. Wherein the smaller the number of subsets in which the servers of a data center participate, the lower the center'"'"'s fragment delivery throughput, the higher the center'"'"'s cost of delivering a fragment, and the higher the likelihood of reducing the amount of bandwidth acquired from that data center by the operator of the system.
66 Citations
17 Claims
-
1. A large scale system, comprising:
-
data centers comprising fractional-storage CDN servers, each server configured to store less than a minimum amount of data needed to decode its stored erasure-coded fragments; assembling devices, each configured to obtain erasure-coded fragments from at least one nonempty subset of the servers, and to measure fragment delivery parameters; and at least one decision component configured to generally improve the measured parameters by occasional change of at least some of the servers of the subsets associated with some of the assembling devices, wherein the occasional change comprises excluding underperforming servers from the subsets; the system configured to exclude underperforming data center by monitoring the fragment-delivery bandwidth utilized by the servers of each data center, and to reduce the bandwidth available to the servers of a data center that was found to utilize less than a certain bandwidth level;
wherein the erasure-coding is rateless-coding enabling a redundancy factor greater than four;
the system comprises;
more than ten data centers scattered across a wide geographical area, more than one hundred servers, each configured to store less than one fifth the minimum amount fragments needed to decode the fragments, and more than ten thousand assembling devices located at user premises and configured to obtain the fragments from the servers via the Internet. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9)
-
-
10. A large scale system, comprising:
data centers comprising fractional-storage CDN servers, each server configured to store less than a minimum amount of data needed to decode its stored erasure-coded fragments; and
assembling devices configured to obtain erasure-coded fragments from nonempty subsets of the servers;
the assembling devices are further configured to measure fragment delivery parameters;
the system configured to generally improve the measured parameters by occasional reselection of the servers of the subsets, wherein the occasional reselection comprises adding to the subsets servers having better fragment delivery parameters compared to the median performance of the servers in the subsets, whereby fragment delivery throughput from a data center is closely related to the number of subsets in which the servers of that data center participate;
the system is further configured to increase the fragment delivery bandwidth available to a data centers whose fragment delivery throughput approaches the center'"'"'s current fragment-delivery bandwidth availability; and
wherein the erasure-coding is rateless-coding enabling a redundancy factor greater than four;
the system comprises;
more than ten data centers spread across a wide geographical area, more than one hundred servers storing fragments with storage gain greater than five, and more than ten thousand assembling devices located at user premises and configured to obtain the fragments from the servers via the Internet.- View Dependent Claims (11, 12, 13, 14, 15, 16, 17)
Specification