On-demand instantiation in a high-performance computing (HPC) system

• US 8,244,882 B2
• Filed: 11/17/2004
• Issued: 08/14/2012
• Est. Priority Date: 11/17/2004
• Status: Active Grant

• Current Assignee: Raytheon Company (Rtx Corporation)
• Original Assignee: Raytheon Company (Rtx Corporation)
• Inventors: Davidson, Shannon V.
• Primary Examiner(s): Meky, Moustafa M
• Assistant Examiner(s): Kim, Hee Soo
• Application Number:
  US10/991,994
• Publication Number:
  US 20060117208A1
• Time in Patent Office: 2,827 Days
• Field of Search: 709/220, 709/224, 709/225, 709/227, 709/228
• US Class Current: 709/228
• CPC Class Codes: H04L 67/1001 for accessing one among a plurality of replicated servers
• CPC Class Codes: H04L 67/1006 with static server selection, e.g. the same server being selected for a specific client
• CPC Class Codes: H04L 67/1008 based on parameters of servers, e.g. available memory or workload monitoring of computer activity G06F11/30
• CPC Class Codes: H04L 67/1023 based on a hash applied to IP addresses or costs

Abstract

In one embodiment, a method for on-demand instantiation in a high-performance computing (HPC) system includes receiving a connection request from a client specifying a first port number and a first host name advertised externally with respect to an HPC server including a cluster of nodes, identifying a service at the HPC server corresponding to the first port number and the first host name, determining whether the identified service is available, and, if the identified service is available, instantiating a host providing the identified service at one or more nodes in the cluster.

Claims

1. A computer-readable medium comprising software that, when executed by a processor, operates to:

receive a connection request from a client specifying a first port number and a first host name, the first port number and the first host name advertised externally with respect to a plurality of nodes, each node comprising a switching fabric integrated to a card and at least two processors integrated to the card;

identify a service at the plurality of nodes, the identified service corresponding to the first port number and the first host name;

determine whether the identified service is available based on one or more aspects of the connection request and one or more rules indicating whether the service is available;

if the identified service is determined to be available based on one or more aspects the connection request and one or more rules indicating whether the service is available, instantiate a host providing the identified service at one or more nodes in the plurality of nodes, wherein instantiating the host comprises using a boot image, a file system, and an operating system (OS) configuration file corresponding to the identified service to boot at least one node in the plurality of nodes in response to the received connection request;

cause a first node of the plurality of nodes to stop providing a second service in response to not detecting one or more requests related to the second service;

cause the first node of the plurality of nodes to provide a third service, the third service being distinct from the second service, after causing the first node to stop providing the second service; and

in response to receiving a request relating to the second service, causing a second node of the plurality of nodes to provide the second service.

2. The computer-readable medium of claim 1, wherein the connection request is a Transmission Control Protocol (TCP) connection request or a User Datagram Protocol (UDP) connection request.

3. The computer-readable medium of claim 1, wherein the software, when executed by the processor, further operates to:

access a list of services at the plurality of nodes comprising a plurality of entries that each specify a service and one or more rules indicating whether the service is available; and

determine, according to the list of services, whether the identified service is available.

4. The computer-readable medium of claim 3, wherein the rules indicate whether the service is available based on a time associated with the connection request from the client.

5. The computer-readable medium of claim 4, wherein the software further operates when executed by the processor to, if the identified service is unavailable based on the time associated with the connection request, block a port on the plurality of nodes corresponding to the first port number to prevent the client from accessing the identified service.

6. The computer-readable medium of claim 1, wherein the software, when executed by the processor, further operates to:

access the boot image, the file system, and the OS configuration file at the plurality of nodes corresponding to the host providing the identified service at one or more nodes in the plurality of nodes; and

use the boot image, the file system and the OS configuration file to instantiate the host providing the identified service at one or more nodes in the plurality of nodes in response to the received connection request.

7. The computer-readable medium of claim 1, wherein the identified service is a web server.

8. The computer-readable medium of claim 1, wherein the software, when executed by the processor, further operates to spoof an address of the host providing the identified service at one or more nodes in the cluster and initiate a connection sequence on behalf of the host while the host is booting, wherein the booting is performed in response to the received connection request.

9. The computer-readable medium of claim 1, wherein:

the address is an Internet Protocol over Media Access Control (IP/MAC) address; and

the connection sequence is a Transmission Control Protocol over IP (TCP/IP) connection sequence or a USER Datagram Protocol (USP) over IP (USP/IP) connection sequence.

10. The computer-readable medium of claim 1, wherein the plurality of nodes comprises nodes coupled to each other according to a topology comprising a three dimensional torus.

11. The computer-readable medium of claim 1, wherein the software, when executed by the processor, further operates to access a list of services at the plurality of nodes comprising a plurality of entries, at least one entry specifying:

the service;

the first port number and the first host name advertised externally with respect to the plurality of nodes; and

a port number and a host name internal to the plurality of nodes that correspond to a host that, when executed at one or more nodes in the plurality of nodes, provides the service.

12. A method comprising:

receiving a connection request form a client specifying a first port number and a first host name, the first port number and the first host name advertised externally with respect to a plurality of nodes, each node comprising a switching fabric integrated to a card and at least two processors integrated to the card;

identifying a service at the plurality of nodes, the identified service corresponding to the first port number and the first host name;

determining whether the identified service is available based on one or more aspects of the connection request and one or more rules indicating whether the service is available;

if the identified service is determined to be available based on one or more aspects the connection request and one or more rules indicating whether the service is available, instantiating a host providing the identified service at one or more nodes in the plurality of nodes, wherein instantiating the host comprises using a boot image, a file system, and an operating system (OS) configuration file corresponding to the identified service to boot at least one node in the plurality of nodes in response to the received connection request;

causing a first node of the plurality of nodes to stop providing a second service in response to not detecting one or more requests related to the second service;

causing the first node of the plurality of nodes to provide a third service, the third service being distinct from the second service, after causing the first node to stop providing the second service; and

in response to receiving a request relating to the second service, causing a second node of the plurality of nodes to provide the second service.

13. The method of claim 12, wherein the connection request is a Transmission Control Protocol (TCP) connection request or a User Datagram Protocol (UDP) connection request.

14. The method of claim 12, further comprising:

accessing a list of services at the plurality of nodes comprising a plurality of entries that each specify a service and one or more rules indicating whether the service is available; and

determining according to the list of services, whether the identified service is available.

15. The method of claim 14, wherein the rules indicate whether the service is available based on a time associated with the connection request from the client.

16. The method of claim 15, further comprising, if the identified service is unavailable based on the time associated with the connection request, blocking a port on the plurality of nodes corresponding to the first port number to prevent the client from accessing the identified service.

17. The method of claim 12, further comprising:

accessing the boot image, the file system, and the OS configuration file at the plurality of nodes corresponding to the host providing the identified service at one or more nodes in the plurality of nodes; and

using the boot image, the file system and the OS configuration file to instantiate the host providing the identified service at one or more nodes the plurality of nodes in response to the received connection request.

18. The method of claim 12, wherein the identified service is a web server.

19. The method of claim 12, further comprising spoofing an address of the host providing the identified service at one or more nodes in the plurality of nodes and initiating a connection sequence on behalf of the host while the host is booting, wherein the booting is performed in response to the received connection request.

20. The method of claim 12, wherein:

the address is an Internet Protocol over Media Access Control (IP/MAC) address; and

the connection sequence is a Transmission Control Protocol over IP (TCP/IP) connection sequence or a User Datagram Protocol (USP) over IP (USP/IP) connection sequence.

21. The method of claim 12, wherein the plurality of nodes comprises nodes coupled to each other according to a topology comprising a three dimensional torus.

22. The method of claim 12, further comprising accessing a list of services at the plurality of nodes comprising a plurality of entries, at least one entry specifying:

the service;

the first port number and the first host name advertised externally with respect to the plurality of nodes; and

a port number and a host name internal to the plurality of nodes that correspond to a host that, when executed at one or more nodes in the cluster, provides the service.

23. A system, comprising:

a memory that stores a list of services at a plurality of nodes, each node comprising a switching fabric integrated to a card and at least two processors integrated to the card;

at least one processor that;

receives a connection request from a client specifying a first port number and a first host name, the first port number and the first host name advertised externally with respect to the plurality of nodes;

identifies a service at the plurality of nodes, the identified service corresponding to the first port number and the first host name;

determines whether the identified service is available based on one or more aspects of the connection request and one or more rules indicating whether the service is available; and

if the identified service is determined to be available based on one or more aspects of the connection request and one or more rules indicating whether the service is available, instantiates a host providing the identified service at one or more nodes in the plurality of nodes, wherein instantiating the host comprises using a boot image, a file system, and an operating system (OS) configuration file corresponding to the identified service to boot at least one node in the plurality of nodes in response to the received connection request;

causes a first node of the plurality of nodes to stop providing a second service in response to not detecting one or more requests related to the second service;

causes the first node of the plurality of nodes to provide a third service, the third service being distinct from the second service, after causing the first node to stop providing the second service; and

in response to receiving a request relating to the second service, causing a second node of the plurality of nodes to provide the second service.

24. The system of claim 23, wherein the connection request is a Transmission Control Protocol (TCP) connection request or a User Datagram Protocol (USP) connection request.

25. The system of claim 23, wherein if the identified service is unavailable based on a time associated with the connection request, the at least one processor blocks a port on the plurality of nodes corresponding to the first port number to prevent the client from accessing the identified service.

26. The system of claim 23, wherein at least one processor:

accesses the boot image, the file system, and the OS configuration file at the plurality of nodes corresponding to the host providing the identified service at one or more nodes in the plurality of nodes; and

uses the boot image, the file system and the OS configuration file to instantiate the host providing the identified service at one or more nodes in the plurality of nodes in response to the received connection request.

27. The system of claim 23, wherein the plurality of nodes comprises nodes coupled to each other according to a topology comprising a three dimensional torus.

28. The system of claim 23, wherein the at least one processor accesses the list of services, the list of services comprising a plurality of entries, at least one entry specifying:

the service;

the first port number and the first host name advertised externally with respect to the plurality of nodes; and

a port number and a host name internal to the plurality of nodes that correspond to a host that, when executed at one or more nodes in the cluster, provides the service.

29. The system of claim 23, wherein at least one processor operates to spoof an address of the host providing the identified service at one or more nodes in the cluster and initiate a connection sequence on behalf of the host while the host is booting, wherein the booting is performed in response to the received connection request.