×

Computer cluster and method for providing a disaster recovery functionality for a computer cluster

  • US 8,843,624 B2
  • Filed: 12/10/2010
  • Issued: 09/23/2014
  • Est. Priority Date: 12/11/2009
  • Status: Active Grant
First Claim
Patent Images

1. A distributed architecture for hosting a server-based application in a virtualized environment inside a cluster of hardware hosts, wherein the same sever-based application is hosted on different hardware hosts of the cluster of hardware hosts, wherein the distributed architecture comprises:

  • virtual instances, configured to run on a hardware host of the cluster of hardware hosts, the virtual instances being connected to external storage, wherein the virtual instances are further configured to be restarted on another hardware host of the cluster of hardware hosts in the event that the hardware host fails;

    a controller comprising a processor, the controller being configured to connect to storage resources, which are enabled for dynamic creation and resizing during operation without interfering with availability or uptime of a virtual instance to which the storage resources are assigned, and which are accessible via network protocols so as to cope with loss of paths or storage redundancy in a multipath configuration of an internet Small Computer System Interface (iSCI) in which an iSCI initiator writes over more than one path to a physical storage resources;

    first agents, wherein the first agents are application programs within the virtual instances, the first agents being configured to receive instructions from the controller, to act on directives issued by the controller, and to report a status of the virtual instances to the controller periodically;

    second agents, wherein the second agents are of a standalone node of a computer cluster, the second agents being configured to receive instructions from the controller and to act on directives issued by the controller;

    ports of the standalone node, which are reserved for providing connectivity to external appliances;

    control domains with which the hardware hosts of the cluster of hardware hosts are equipped, the control domains being configured to require an infrastructural process embedded into the control domain, wherein the infrastructural process acts;

    in case of a disaster, orduring a reboot of the local control domain or parts of the hardware hosts of the cluster of hardware hosts, orin the wake of hardware faults,or any combination thereof;

    a communication system comprising a processor, the communication system being included in the control domains, the communication system being configured to contact other control domains and to distribute configuration data over all the control domains, with the configuration data being stored in databases of flat file systems in the control domains;

    a management system comprising a processor, wherein the management system is logically superior to the control domains, the management system being enabled to act as a single redundancy controller by being configured to restart the virtual instances on the another hardware host of the cluster of hardware hosts that it has access to, the management system further being multi-tenancy enabled and able to run inside one of the virtual instances in the cluster of hardware hosts that it manages, and the management system further being configured to enable creation of elements in a data center centrally to maintain a configuration database;

    a first compartment comprising a plurality of first physical nodes configured to provide first resources for guest virtual instances, each of the plurality of first physical nodes comprising a first mass storage device, the first mass storage device comprising;

    a first partition provided for booting the first physical node; and

    a second partition as part of the first resources; and

    a second compartment comprising a plurality of second physical nodes configured to provide second resources for guest virtual instances, each of the plurality of second physical nodes comprising a second mass storage device, the second mass storage device comprising;

    a third partition provided for booting the second physical node; and

    a fourth partition as part of the second resources;

    wherein the first and the second physical nodes are configured to provide third resources for a plurality of storage management processes;

    wherein each of the plurality of first physical nodes and the plurality of second physical nodes is provided for at least one of the plurality of storage management processes; and

    wherein the storage management processes are configured for monitoring each other.

View all claims
  • 2 Assignments
Timeline View
Assignment View
    ×
    ×