Abstract: Distributing pull protocol requests via a relay server and thereby reducing the number of outgoing packets used by a fragment pull protocol, including the steps of aggregating, by an assembling device, a plurality of fragment pull protocol requests into an aggregated message; transmitting the aggregated message to a relay server, whereby the relay server distributes the requests to at least two fractional-storage servers; and receiving, by the assembling device from the at least two fractional-storage servers, a plurality of fragments in response to the aggregated message.

Abstract: Controlling fragment load on shared links, including a large number of fractional-storage CDN servers storing erasure-coded fragments encoded with a redundancy factor greater than one from contents, and a large number of assembling devices configured to obtain the fragments from sub-sets of the servers. At least some of the servers share their Internet communication link with other Internet traffic, and the fragment traffic via the shared link is determined by the number of sub-sets in which the servers accessed via the shared link participate. Wherein the maximum number of sub-sets in which the servers accessed via the shared link are allowed to participate is approximately a decreasing function of the throughput of the other Internet traffic via the shared link.

Abstract: Reduction of peak-to-average traffic ratio in distributed streaming systems, including a large number of fractional-storage CDN servers accessed via the Internet, and storing erasure-coded fragments encoded with a redundancy factor greater than one from streaming contents, and a very large number of assembling devices obtaining the fragments from the servers in order to reconstruct the streaming contents. The assembling devices are spread over different time zones spanning at least three hours and balance the bandwidth load between the servers.

Abstract: Fault tolerance in a distributed streaming system including fractional-storage CDN servers storing erasure-coded fragments encoded with a redundancy factor greater than one from segments of streaming contents. Each server delivers fragments, at a certain fragment delivery throughput, to multiple assembling devices using a fragment pull protocol, wherein a reduction in the fragment delivery throughput of one of the servers triggers a process in which at least some of the other servers approximately immediately increase their fragment delivery throughput as a reaction to the fragment pull protocol, to compensate for the reduced throughput.

Abstract: Load-balancing a distributed system by replacing overloaded servers, including the steps of retrieving, by an assembling device using a fragment pull protocol, erasure-coded fragments associated with segments, from a set of fractional-storage servers. Occasionally, while retrieving the fragments, identifying at least one server from the set that is loaded to a degree requiring replacement, and replacing, using the fragment pull protocol, the identified server with a substitute server that is not loaded to the degree requiring replacement. Wherein the substitute server and the remaining servers of the set are capable of delivering enough erasure-coded fragments in the course of reconstructing the segments.

Abstract: Source-selection based Internet backbone traffic shaping, including the steps of assessing a large number of network paths through which erasure-coded fragments usually flow when transmitted from a large number of relevant fractional-storage CDN servers to an assembling device; accessing preferences for fragment delivery via many of the paths; and selecting the servers whose assessed paths fit well the preferences for fragment delivery to the assembling device. Wherein the servers are accessed via the Internet, not all servers are connected to the Internet via the same networks, and the erasure-coded fragments are encoded with a redundancy factor greater than one from contents.

Abstract: A system including a plurality of fractional-storage servers and a plurality of peer-to-peer devices. Substantially each of the servers and peer-to-peer devices stores less than a minimum amount of erasure-coded fragments needed to decode segments of streaming content. The system delivers at least the minimum amount of erasure-coded fragments needed to decode the segments of streaming content, from any group of the servers, or group of the servers plus peer-to-peer devices, that together store at least the minimum amount of erasure-coded fragments needed to decode the segments of streaming content. Optionally, the system supplements streaming capabilities of the servers during peak traffic periods by sending erasure-coded fragments stored on the peer-to-peer devices during the peak traffic periods.

Abstract: Receiving streaming content from servers located around the globe, including the following steps: requesting via the Internet, by an assembling device which may be located almost anywhere around the globe, using a fragment pull protocol, a set of erasure-coded fragments associated with segments off streaming content, from a plurality of fractional-storage servers which may be located almost anywhere around the globe. And compensating for lost fragments by requesting additional erasure-coded fragments that are needed to reconstruct the segments. Wherein the bandwidth of the streaming content is bounded approximately only by the incoming bandwidth of the assembling device.

Abstract: Load-balancing an asymmetrical distributed erasure-coded system including fractional-storage CDN servers, storing, at a high storage gain, erasure-coded fragments encoded with a redundancy factor greater than one from segments, and a plurality of assembling devices, each obtaining fragments from a subgroup of the servers. The subgroups are selected from the servers still capable of increasing their fragment delivery throughput. Wherein not all of the servers have the same fragment delivery bandwidth capability, and the storage gain of each segment on each server is usually not strictly proportional to the bandwidth capability of the server, and the aggregated throughput used by the servers to deliver fragments may approach the aggregated bandwidth capabilities of the servers.

Abstract: An assembling device obtaining enough erasure-coded fragments from fractional-storage CDN servers for reconstructing a first set of segments including at least one segment. The communication between the assembling device and the servers is subject to at least one type of communication fault, and the assembling device handles the communication faults by approximately randomly selecting on-the-fly servers from which to obtain additional fragments instead of fragments that failed to be obtained.

Abstract: Fast retrieval and progressive retransmission of content, including the steps of obtaining erasure-coded fragments by an assembling server from fractional-storage CDN servers; reconstructing a streaming content file from the obtained fragments; and streaming the reconstructed content or a transcoded version of the content by the assembling server to a client device. Wherein most of the fractional-storage CDN servers are located close to or on the Internet backbone, and streaming the reconstructed content takes at least an order of magnitude longer than obtaining the fragments and reconstructing the content.