Granted Patent B2

US 8,787,391 · App. 12/603,678 · Granted Jul 22, 2014

Abstract

Claims (39)

1. A method implemented and residing within a non-transitory computer-readable storage medium that is executed by one or more processors of a network to perform the method, comprising:

configuring network nodes of the network to detect network packets of a predefined type and to forward those network packets among the network nodes without removing the network packets from the network, the network packets are identified as memory objects of the network,

each network node retrieves particular memory objects of the predefined type and reinserts those particular memory objects, without storing those particular memory objects on that node, back into the network for acquisition and inspection by other ones of the network nodes when that network node determines that the particular memory objects are not needed by particular applications residing on that network node; and

using, by each of the network nodes, the network packets that are cyclically traversing the network as a memory device shared among the network nodes, information housed in the memory objects resides in network transmission lines and bandwidth of the network without being written to memory or storage of any of the network nodes operating on the network until consumed or needed by applications interfaced to the network nodes, wherein configuring further includes configuring the network nodes to take a copy of particular ones of the network packets that applications in communication with the network nodes are looking for or requesting, and once the copy is taken the particular ones of the network packets are re-injected into the network by the network nodes.

2. The method of claim 1 , wherein configuring further includes configuring the network nodes to use two or more different communication paths when forwarding the network packets throughout the network.

3. The method of claim 1 , wherein configuring further includes identifying a special network node to continually inspect each of the network packets and verify a digital signature for each of the network packets.

4. The method of claim 3 , wherein identifying further includes configuring the special network node to remove each network packet from the network when that network packet's digital signature is invalid.

5. The method of claim 1 , wherein configuring further includes configuring the network nodes to compare an expiration date and time stamp for each of the network packets against a current date and time for the network and then to purge particular network packets from the network when the current date and time is equal to or is past the expiration date and time stamp.

6. The method of claim 1 , wherein configuring further includes configuring the network nodes to flush particular network packets to the storage or the memory of the network nodes when evaluation of a policy indicates that the particular network packets are to be flushed to the storage or the memory.

7. The method of claim 1 , wherein configuring further includes at least one of:

configuring the network nodes to use a predefined channel of the network when forwarding the network packets throughout the network; and

configuring a logging node to log the network packets satisfying a logging filter applied by the logging node for subsequent evaluation.

8. A method implemented and residing within a non-transitory computer-readable storage medium that is executed by one or more processors of a node on a network to perform the method, comprising:

detecting one or more network packets on the network as being associated with a network memory object that is cyclically traversing the network using the network as a memory device where the network memory object and information housed in the network memory object reside on network transmission lines of the network and does not reside on any specific network node operating on the network until an application interfaced to the specific network node consumes or needs the memory object;

copying the memory object off the network as a copied memory object when the network memory object includes a predefined tag indicating that the application needs the memory object, otherwise the network memory object is not copied and is reinserted back into the network for delivery and inspection by other nodes of the network;

passing the copied memory object to a service that is configured to process the copied memory object when the application needs the memory object; and

injecting the network memory object back into the network over the network transmission lines for use by other nodes of the network when the application needs the memory object.

9. The method of claim 8 , wherein detecting further includes buffering and ordering the one or more network packets to assemble the network memory object from the network.

10. The method of claim 8 , wherein copying further includes determining at the node that the node is a first node to receive the network memory object on the network and in response thereto sending an acknowledgement to a sending node that injected the network memory object thereby permitting the sending node to remove the network memory object from memory of the sending node.

11. The method of claim 8 , wherein copying further includes determining that a lock set on the network memory object has exceeded a predefined elapsed period of time and removing the lock from the network memory object and the copied memory object and removing the lock before the network memory object is injected back into the network.

12. The method of claim 8 , wherein copying further includes at least one of:

maintaining metadata file semantics, flags, and keys that existed with the network memory object in the copied memory object before passing the copied memory object to the service; and

injecting a new memory object into the network having new metadata created and associated with that new memory object.

13. The method of claim 8 , wherein passing further includes:

receiving a lock request from the service; and

setting a lock flag on the network memory object before injecting the network memory object back into the network.

14. The method of claim 13 further comprising:

receiving a modified version of the copied memory object back from the service after the network memory object had already been injected back into the network; and

performing one of:

waiting for the network memory object to be detected on the network at the node a second time and then replacing the network memory object with the modified version of the copied memory object with the lock removed back into the network; and

injecting the modified version of the copied memory object with the lock removed back into the network and then remove the network memory object when the network memory object is detected on the network the second time.

15. The method of claim 8 further comprising:

receiving a second memory object in an encrypted format from the service;

receiving a public key from the service, that public key has to be used in combination with one or more private keys associated with one or more second nodes of the network to decrypt the second memory object;

injecting the second memory object into the network and delaying the injection of the public key into the network until a policy is satisfied; and

removing the public key from memory and storage of the node once the public key is injected into the network.

16. The system of claim 14 , wherein the memory objects maintain metadata while on the network, the metadata used for security management, content type identification, and file management.

17. The system of claim 14 , wherein each of the first and the second network memory device services are further configured to copy select ones of the memory objects off the network and provide those select memory objects to one or more additional services that process the select memory objects.

18. The system of claim 14 , wherein the first and second nodes are network routers or network proxy devices.

Assignments (16)