Loading patent…
AssigneeNetli, Inc.
InventorsAdam J. Grove, Michael Kharitonov, Alexei Tumarkin
Estimating the term…
The invention uses a distributed network of specialized nodes of different types dispersed around the Internet. In operation, web client's requests are directed to a node of a first type chosen to be close to the client, and the client communicates with this node using a standard protocol such as HTTP. This first node receives the request, and locates a node of a second type, chosen to be an optimal initial relay on a path to the web server. The first node may communicates the request to the second node using a different, specialized, protocol that has been designed for improved performance and specifically to reduce traffic volume and to reduce latency. The second node receives communication from the first node using this specialized protocol, and relays it to an optimally chosen third node using the same, or possibly different internode communication protocol. This process may repeat over additional internode hops until finally, the last node receives the request from the previous network node, converts it back to a standard protocol such as HTTP, and forwards the request to the server. Responses from server to client can take the same or similar reverse route, and can also be carried over specialized protocols between the network nodes. In addition, these nodes can employ other techniques such as web caches that avoid or improve some communication steps.
A method for communicating an Internet message between a source and a destination over the Internet, comprising:
A method for communicating an Internet message between a source and a destination over the Internet, comprising:
A system for communicating an Internet message from a source to a destination over the Internet, comprising:
A system for communicating an Internet message from a source to a destination over the Internet, comprising:
A system for communicating an Internet message from a source to a destination over the Internet, comprising:
A system for communicating an Internet message from a source to a destination over the Internet, comprising:
A system for communicating an Internet message from a source to a destination over the Internet, comprising:
A system for communicating an Internet message from a source to a destination over the Internet, comprising:
A method for communicating an Internet message between a source and a destination, comprising:
A system for communicating Internet messages between a source and a destination, comprising:
Dependencies are inferred from the claim text.
Drawings are temporarily unavailable. Open the PDF at USPTO
From the US filing history. Foreign family members aren’t listed.
Server selection for load balancing: based on parameters of servers, e.g. available memory or workload
Protocols: based on web technology, e.g. hypertext transfer protocol [HTTP]
In which an application is distributed across nodes in the network: for accessing one among a plurality of replicated servers
Server selection for load balancing: based on network conditions
Term ended 12 May 2020 (estimated)
The invention relates to communication between web clients, such as browsers, and web servers, where the communication is carried at least in part over the Internet or any other network layer in which bandwidth usage and communication latency are of concern.
Today, improving the performance of Internet communication is of major technological and commercial concern. Investment in improving the Internet network infrastructure is estimated to become a $1.3 trillion dollar industry by 2003 (Source: Nortel Industries press release Jan. 31, 2000). It has been estimated that many web users will not tolerate a delay in downloading a web page of more than about 8 seconds, and that the current value of e-commerce sales at risk because of slow download speeds is $4.35 billion per year. (Source: Zona Research report “The need for speed”, abstract available http://www.zonaresearch.com/info/press/99-jun30.htm). In this climate there is pressing demand for ways to improve web performance, and no simple or obvious techniques are overlooked.
The invention presented here is a technique that offers significant Internet performance gains, can be deployed at relatively modest cost in less than a year, and needs neither major infrastructure changes nor changes to end-user software.
As shown in the drawing, the invention comprises a distributed collection 100 of specialized computers or network nodes, of three types hereafter called C-nodes 110, I-nodes 120 and S-nodes 130 (although it is possible that the functionality of any two or even all three node types may be present in a single physical device). As discussed below, certain embodiments of the invention include other components in addition to C-nodes, I-nodes and S-nodes such as clients 140 and servers 150. These nodes may also be embodied as computer software executing on a general-purpose computer that also serves other purposes, or may be embodied as a tightly-coupled cluster of computers. C-nodes are distributed throughout the network with the intent that most Internet users will be close, in network terms, to at least one C-node. In particular, C-nodes may be placed on Internet Service Providers' (ISP) premises, on large corporate networks, on Internet backbone networks, and elsewhere. Correct operation of the invention does not depend on how well the C-nodes are located, although the benefits that are delivered by the invention may depend on this.
I-nodes are distributed within the interior of the network with the intent of establishing different controlled paths between C-nodes and S-nodes. These paths, determined by the choice of different I-nodes, can be constantly monitored using specialized software running on I-nodes. In particular, I-nodes may be placed to isolate slower links, or links that are more prone to packet loss. Correct operation of the invention does not depend on particular locations of the I-node, although the extent of the benefits that are delivered by the invention may vary depending on the locations chosen. In a preferred embodiment, the invention includes or uses means such that certain web traffic, including requests for web content, is communicated to a C-node instead of being communicated directly to the server that would ordinarily deliver such content. These means should have the property that the chosen C-node for any request be close to the originator of the request (hereafter, the “client”). The notion of closeness used can include any combination of such metrics as bandwidth capacity, bandwidth cost, latency, security, administrative boundaries, administrative convenience, current congestion on various network paths, and geographic proximity, although other factors may also be taken into account. However correct operation of the invention does not depend on which notion of closeness is used, or how close the chosen C-node actually is.
Regardless of which means are chosen, we call the component of the system that arranges for traffic to be sent to a close C-node, or automatically pass through such a C-node, the redirection system. In the following, we list six means, numbered R1 through R6, that can be used within the redirection component of our invention. However, this list is not complete and the invention contemplates other means that can be used instead. Finally, as anyone skilled in the art will appreciate, many combinations or variants of methods in the following list can serve as redirection means.