COMPUTING INFRASTRUCTURE

• US 20090216910A1
• Filed: 11/13/2008
• Published: 08/27/2009
• Est. Priority Date: 04/23/2007
• Status: Active Grant

• Current Assignee: David D. Duchesneau
• Original Assignee: David D. Duchesneau
• Inventors: DUCHESNEAU, DAVID D.
• Granted Patent: US 8,706,914 B2
• Time in Patent Office: Days
• US Class Current: 709/250
• CPC Class Codes: F25D 17/02 for circulating liquids, e.g. brine
• CPC Class Codes: F28D 15/0266 with separate evaporating and condensing chambers connected by at least one conduit; Loop-type heat pipes; with multiple or common evaporating or condensing chambers F28D15/043 takes precedence
• CPC Class Codes: F28D 15/06 Control arrangements therefor
• CPC Class Codes: F28F 1/00 Tubular elements; Assemblies of tubular elements specially adapted for movement F28F5/00
• CPC Class Codes: F28F 2250/08 Fluid driving means, e.g. pumps, fans
• CPC Class Codes: G06F 9/5072 Grid computing
• CPC Class Codes: H01B 3/24 containing halogen in the molecules, e.g. halogenated oils
• CPC Class Codes: H04L 2463/141 Denial of service attacks against endpoints in a network
• CPC Class Codes: H04L 41/00 Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
• CPC Class Codes: H04L 41/04 Network management architectures or arrangements
• CPC Class Codes: H04L 41/0816 the condition being an adaptation, e.g. in response to network events
• CPC Class Codes: H04L 63/20 for managing network security; network security policies in general filtering policies H04L63/0227
• CPC Class Codes: Y04S 40/20 Information technology specific aspects, e.g. CAD, simulation, modelling, system security

Abstract

An affordable, highly trustworthy, survivable and available, operationally efficient distributed supercomputing infrastructure for processing, sharing and protecting both structured and unstructured information. A primary objective of the SHADOWS infrastructure is to establish a highly survivable, essentially maintenance-free shared platform for extremely high-performance computing (i.e., supercomputing)—with “high performance” defined both in terms of total throughput, but also in terms of very low-latency (although not every problem or customer necessarily requires very low latency)—while achieving unprecedented levels of affordability at its simplest, the idea is to use distributed “teams” of nodes in a self-healing network as the basis for managing and coordinating both the work to be accomplished and the resources available to do the work. The SHADOWS concept of “teams” is responsible for its ability to “self-heal” and “adapt” its distributed resources in an “organic” manner. Furthermore, the “teams” themselves are at the heart of decision-making, processing, and storage in the SHADOWS infrastructure. Everything that'"'"'s important is handled under the auspices and stewardship of a team.

Claims

1. A system comprising geographically distributed computing subsystems (“

SHADOWS nodes”

) that are relatively distant from one another, each of which is capable of carrying out at least a limited set of functions to include communications, data and cryptographic processing, memoization, and data storage and retrieval, and where each such node recognizes, establishes trust, and collaborates with—

other nodes of the same system. In general, SHADOWS nodes communicate via WAN (wide-area network) links (to include MAN, or metro-area network links, and RAN, or regional-area network links, and other links to relatively non-local destinations), including both terrestrial and non-terrestrial wireless communications.

2. The system described in claim 1, where each SHADOWS node mutually associates with selected other qualified and trusted SHADOWS nodes in order to form a multiplicity of higher-level collaborative system survival units (“

SHADOWS teams”

), where each SHADOWS node is, geographically speaking, relatively closer to some team members and relatively much more distant to others, and where each such team is jointly and severally accountable for a portion of the aggregate responsibilities of the overall system.

3. The system described in claim 1, where each SHADOWS node timely publishes selected general resource information to other SHADOWS nodes, and also publishes team-specific resource information to its fellow team members for each team to which it belongs.

4. The system described in claim 3, where each SHADOWS node “

volunteers”

its readiness (according to its operational profile and relative “

survivability”

factors, such as resource availability, vulnerabilities, threat exposure, etc.) to accept selected portions of the immediate responsibilities of other SHADOWS nodes as its own, while also delegating selected portions of its immediate responsibilities to other qualified SHADOWS nodes on a similar basis, as appropriate, so as to meet outstanding SLAs (service level agreements) and/or other operational goals (e.g., such as maximize throughput and/or survivability, minimize latency, risk, and operational expense, etc.).

5. The system described in claim 4, where SHADOWS nodes dynamically and autonomically self-modify or otherwise adapt their collective operational profile and associated readiness so as to economize operational resources and/or optimize their collective survivability while maintaining the necessary trust relationships and continuing to fulfill SLA-related commitments as appropriate. (Note that a SHADOWS node or other resource that is no longer trusted in one or more operational roles is effectively removed from those roles, but might still be trustworthy in other roles, or may re-establish its trustworthiness, and thus dynamically changing trust relationships directly bear on the operational configuration, profile, readiness, and survivability of the system'"'"'s components, but not necessarily on the externally visible operation, functionality, performance, or survivability of the overall system.)

6. The system described in claim 5, where the periodic and/or temporary availability of lower cost or otherwise opportunistic resources (such as insolation for a solar-powered energy plant, strong winds for a wind-powered energy plant, waste methane for a gas-powered energy plant, surplus bandwidth on a network communications plan, etc.) are automatically taken advantage of by autonomically shifting the resource utilization (e.g., computing load) among SHADOWS nodes to follow the resource availability, to the extent it can be accomplished without jeopardizing committed levels of survivability.

7. The system described in any of claims 1-6, where each SHADOWS node is itself a subsystem comprising a set of geographically distributed computing subsystems (“

SCRAM nodes”

) that are generally in relatively closer proximity to each other than the SHADOWS nodes are to each other, and where each SCRAM node is capable of carrying out at least a limited set of functions to include communications, data and cryptographic processing, memoization, and data storage and retrieval.

8. A system comprising distributed computing subsystems (“

SCRAM nodes”

) that are relatively local to one another (in contrast to SHADOWS nodes, which are relatively distant to each other), each of which is capable of carrying out at least a limited set of functions to include communications, data and cryptographic processing, memoization, and data storage and retrieval, and where each such node recognizes, establishes trust, and collaborates with—

other nodes of the same system. In general, SCRAM nodes communicate via a combination of LAN (local-area network) and WAN (wide-area network) links, including both terrestrial and non-terrestrial wireless communications, although non-LAN links are used primarily to augment LAN links and provide increased inter-connectivity, bandwidth and survivability, and thus are typically short-circuited by exploiting localized paths held in common to the extent possible.

9. The system described in claim 8, where each SCRAM node mutually associates with selected other qualified and trusted SCRAM nodes in order to form a single, relatively local SHADOWS node, and to participate in a multiplicity of higher-level collaborative system survival units (“

SHADOWS teams”

). (NOTE;

If such a set of SCRAM nodes is so localized that it may be concentrated and physically packaged into a single entity comprising a multiplicity of logical SCRAM nodes, it may be referred to as a SCRAM machine or SCRAM unit. A less-dense configuration of SCRAM nodes that cannot be physically packaged into a single entity may be referred to as a SCRAM “

mesh,”

which is essentially a logical SCRAM machine. Either configuration may be sufficient to collectively form a local SHADOWS node, but acceptance of the configuration as a SHADOWS node is strictly up to the other SHADOWS nodes with which it wishes to become a peer.)

10. The system described in claims 8 and 9, where each SCRAM node timely publishes selected general resource information to other SCRAM nodes, and also publishes team-specific resource information to its fellow team members for each team to which it belongs.

11. The system described in claim 10, where each SCRAM node “

volunteers”

its readiness (according to its operational profile and relative “

survivability”

factors, such as resource availability, vulnerabilities, threat exposure, etc.) to accept selected portions of the immediate responsibilities of other SCRAM nodes as its own, while also delegating selected portions of its immediate responsibilities to other qualified SCRAM nodes on a similar basis, as appropriate, so as to meet outstanding SLAs (service level agreements) and/or other operational goals (e.g., such as maximize throughput and/or survivability, minimize latency, risk, and operational expense, etc.).

12. The system described in claim 11, where SCRAM nodes dynamically and autonomically self-modify or otherwise adapt their collective operational profile and associated readiness so as to economize operational resources and/or optimize their collective survivability while maintaining the necessary trust relationships and continuing to fulfill SLA-related commitments as appropriate. (Note that a SCRAM node or other resource that is no longer trusted in one or more operational roles is effectively removed from those roles, but might still be trustworthy in other roles, or may re-establish its trustworthiness, and thus dynamically changing trust relationships directly bear on the operational configuration, profile, readiness, and survivability of the system'"'"'s components, but not necessarily on the externally visible operation, functionality, performance, or survivability of the overall system.)

13. The system described in claim 12, where the periodic and/or temporary availability of lower cost or otherwise opportunistic resources (such as insolation for a solar-powered energy plant, strong winds for a wind-powered energy plant, waste methane for a gas-powered energy plant, surplus bandwidth on a network communications plan, etc.) are automatically taken advantage of by autonomically shifting the resource utilization (e.g., computing load) among SCRAM nodes to follow the resource availability, to the extent it can be accomplished without jeopardizing committed levels of survivability.

14. The system described in any of claims 8 through 13, where each SCRAM node is itself a subsystem comprising a set of locally distributed computing subsystems (“

MASTER/SLAVE nodes”

) that are generally in very close proximity to each other (much more so than the SCRAM nodes are to each other), and where each MASTER/SLAVE node is capable of carrying out at least a limited set of functions to include communications, data and cryptographic processing, memoization, and data storage and retrieval.

15. A system implementing a miniature, self-contained, unmanned, secure (often outdoors or underground) supercomputing “

datacenter,”

comprising a multiplicity of SCRAM nodes, along with one or more self-contained power plants capable of operating off-grid (off the utility power grid) for extended periods (to include permanently), and designed to be physically visited for maintenance purposes as infrequently as every few years, but at most only once or twice a year (and these may be combined with scale-up visits). (NOTE;

Depending upon its available resources, a single SUREFIRE system may fully implement a single SHADOWS node). NOTE;

SUREFIRE sites can be located on virtually any outdoors property, but also in basements or on rooftops, etc. SUREFIRE sites usually include one or more renewable energy systems, in addition to conventional energy sources. SUREFIRE sites are designed for maximal energy efficiency, and emit very little waste heat. All SUREFIRE sites are expendable without data loss, and penetration can never yield useful information to an attacker.

16. The system described in claim 15, augmented by a FRAME subsystem (“

Forced Recuperation, Aggregation &

Movement of Energy”

), where the heat energy caused by the various SUREFIRE subsystems is recuperated and reused, with transformation as necessary, such that it either reduces the load on internal or external power generation, or contributes to internal power generation, or both.

17. The system described in claim 16, where one or more of the self-contained power plants is implemented through the use of renewable energy sources, such as through incorporating any combination of the BLOOMER, FLOWER, and SOLAR subsystems.

18. The system described in claim 17, where the exposure to hazards introduced by the use of renewable energy sources is reduced or otherwise mitigated, and the production of power is improved or otherwise managed, with the help of any combination of the DEFEND, WARN, LISTEN, and PODIUM subsystems.

19. The system described in any of claims 15 through 18, where the analytic, planning, and other computing and reasoning capabilities of the system (and in particular, the system'"'"'s internal SCRAM nodes), in conjunction with similar capabilities of peer systems located elsewhere, are engaged to recognize threats to its own survival and the survival of its peers, to protect itself (including both the physical asset and its information content), and to protect the overall system of which it is a part.

20. A system comprising distributed computing subsystems (“

SCRAM nodes”

) that are relatively local to one another (in contrast to SHADOWS nodes, which are relatively distant to each other), each of which is capable of carrying out at least a limited set of functions to include communications, data and cryptographic processing, memoization, and data storage and retrieval, and where each such node recognizes, establishes trust, and collaborates with—

other nodes of the same system. In general, SCRAM nodes communicate via a combination of LAN (local-area network) and WAN (wide-area network) links, including both terrestrial and non-terrestrial wireless communications, although non-LAN links are used primarily to augment LAN links and provide increased inter-connectivity, bandwidth and survivability, and thus are typically short-circuited by exploiting localized paths held in common to the extent possible.