Abstract: This disclosure describes, generally, methods and systems for implementing memory overcommit of virtual machines. The method includes establishing a plurality of virtual machines on a physical machine, broadcasting, from each of the plurality of virtual machines to a central scheduler, resource usage requirements, and then based at least in part on the resource usage requirements broadcasted from each of the plurality of virtual machines, determining a resource requirements schedule for each of the plurality of virtual machines. The method further includes receiving at least one resource request from at least one of the plurality of virtual machines, based on the resource requirements schedule, un-assigning resources from at least one of the plurality of virtual machines, and assigning the un-assigned resources to the at least one of the plurality of virtual machines which initiated the resource request.

Abstract: The present disclosure is directed to a protection scheme for remotely-stored data. A system may comprise, for example, at least one device including at least one virtual machine (VM) and a trusted execution environment (TEE). The TEE may include an encryption service to encrypt or decrypt data received from the at least one VM. In one embodiment, the at least one VM may include an encryption agent to interact with interfaces in the encryption service. For example, the encryption agent may register with the encryption service, at which time an encryption key corresponding to the at least one VM may be generated. After verifying the registration of the encryption agent, the encryption service may utilize the encryption key corresponding to the at least one VM to encrypt or decrypt data received from the encryption agent. The encryption service may then return the encrypted or decrypted data to the encryption agent.

Abstract: This disclosure describes, generally, methods and systems for implementing memory overcommit of virtual machines. The method includes establishing a plurality of virtual machines on a physical machine, broadcasting, from each of the plurality of virtual machines to a central scheduler, resource usage requirements, and then based at least in part on the resource usage requirements broadcasted from each of the plurality of virtual machines, determining a resource requirements schedule for each of the plurality of virtual machines. The method further includes receiving at least one resource request from at least one of the plurality of virtual machines, based on the resource requirements schedule, un-assigning resources from at least one of the plurality of virtual machines, and assigning the un-assigned resources to the at least one of the plurality of virtual machines which initiated the resource request.

Abstract: This disclosure describes, generally, methods and systems for implementing memory overcommit of virtual machines. The method includes establishing a plurality of virtual machines on a physical machine, broadcasting, from each of the plurality of virtual machines to a central scheduler, resource usage requirements, and then based at least in part on the resource usage requirements broadcasted from each of the plurality of virtual machines, determining a resource requirements schedule for each of the plurality of virtual machines. The method further includes receiving at least one resource request from at least one of the plurality of virtual machines, based on the resource requirements schedule, un-assigning resources from at least one of the plurality of virtual machines, and assigning the un-assigned resources to the at least one of the plurality of virtual machines which initiated the resource request.

Abstract: The present disclosure is directed to a protection scheme for remotely-stored data. A system may comprise, for example, at least one device including at least one virtual machine (VM) and a trusted execution environment (TEE). The TEE may include an encryption service to encrypt or decrypt data received from the at least one VM. In one embodiment, the at least one VM may include an encryption agent to interact with interfaces in the encryption service. For example, the encryption agent may register with the encryption service, at which time an encryption key corresponding to the at least one VM may be generated. After verifying the registration of the encryption agent, the encryption service may utilize the encryption key corresponding to the at least one VM to encrypt or decrypt data received from the encryption agent. The encryption service may then return the encrypted or decrypted data to the encryption agent.

Abstract: According to an aspect of the present invention, nodes for hosting of new virtual machines (VM) are selected according to approaches designed to reduce power consumption in a grid. In an embodiment, the approaches are designed to facilitate the possibility of freeing one or more nodes from hosting VMs to power down the nodes, thereby reducing power consumption. Thus, an example approach is based on provisioning a new VM on a node which currently (immediately prior to provisioning) has the maximum resource consumption. Another example approach is based on provisioning a new VM on a node which currently has small-sized VMs in terms of resource requirements. In yet another embodiment, the approach is based on provisioning a new VM on a node located in a geographical area having low power tariffs.

Abstract: Virtual machines can be pre-created in a grid environment. Pre-created machines can be of a tiny configuration to avoid consuming resources. A request for a virtual machine in the grid can be granted by ballooning a pre-created tiny virtual machine to a larger configuration. The tiny pre-created virtual machine can be advertised as being of a non-tiny configuration. Agents can work in concert to coordinate handing requests for a virtual machine in the grid. The virtual machine can be initialized before it is reduced to a tiny configuration. Ballooning the virtual machine can take considerably less time than creating it from scratch. Thus, high performance computing can be provided on virtual machines in a grid environment, enabling virtual machine technology to be applied in a wide variety of grid-based scenarios.

Abstract: An aspect of the present invention mitigates reduction in availability level during maintenance of nodes in a cluster. In one embodiment, on receiving an indication that a maintenance activity is to be performed on the cluster, a scaling out of the cluster is first performed to add some nodes having the maintenance activity already performed, followed by a scaling in of the cluster to remove some of the nodes in the cluster which do not yet have the maintenance activity performed. The scaling out is performed before any scaling in of the cluster such that the number of nodes available in the cluster after the scaling in is not less than the number of nodes in the cluster at the time of receiving the indication. Accordingly, the reduction in availability level (which is based on the number of nodes available) is mitigated.

Abstract: An aspect of the present invention reduces the recovery time for business organizations in case of disasters. In one embodiment, a disaster recovery system containing a primary site and a backup site (implemented as a cluster) is maintained. Application instances are executed in both the primary site and the backup site, with the number of instances executed on the backup site being fewer than that executed on the primary site. During normal operation, user requests received are processed using only the instances executing in the primary site, while the instances executing in the backup site are used in a standby state. On identifying that a disaster has occurred, the user requests received immediately after identification of the disaster are processed using only the instances executing in the backup site. The cluster at the backup site is then scaled out to add application instances until a desired level/percentage is achieved.

Abstract: Reducing access time for data in a file system when seek requests are received ahead of access requests. In one embodiment, an operating system providing access to the file system receives a seek request (from a user application) indicating an identifier of a file and a location within the file at which a data is sought to be accessed. In response, the operating system computes the offset of a disk block containing the location (thereby the data that is sought to be accessed). On receiving an access request (after the seek request from the same user application) indicating an operation to be performed on the data, the operating system executes the operation on the data using the pre-computed offset of the disk block. The computation of the disk block is performed before the access request is received thereby reducing the time required to process the access request.

Abstract: This disclosure describes, generally, methods and systems for implementing memory overcommit of virtual machines. The method includes establishing a plurality of virtual machines on a physical machine, broadcasting, from each of the plurality of virtual machines to a central scheduler, resource usage requirements, and then based at least in part on the resource usage requirements broadcasted from each of the plurality of virtual machines, determining a resource requirements schedule for each of the plurality of virtual machines. The method further includes receiving at least one resource request from at least one of the plurality of virtual machines, based on the resource requirements schedule, un-assigning resources from at least one of the plurality of virtual machines, and assigning the un-assigned resources to the at least one of the plurality of virtual machines which initiated the resource request.

Abstract: According to an aspect of the present invention, nodes for hosting of new virtual machines (VM) are selected according to approaches designed to reduce power consumption in a grid. In an embodiment, the approaches are designed to facilitate the possibility of freeing one or more nodes from hosting VMs to power down the nodes, thereby reducing power consumption. Thus, an example approach is based on provisioning a new VM on a node which currently (immediately prior to provisioning) has the maximum resource consumption. Another example approach is based on provisioning a new VM on a node which currently has small-sized VMs in terms of resource requirements. In yet another embodiment, the approach is based on provisioning a new VM on a node located in a geographical area having low power tariffs.

Abstract: An aspect of the present invention reduces the recovery time for business organizations in case of disasters. In one embodiment, a disaster recovery system containing a primary site and a backup site (implemented as a cluster) is maintained. Application instances are executed in both the primary site and the backup site, with the number of instances executed on the backup site being fewer than that executed on the primary site. During normal operation, user requests received are processed using only the instances executing in the primary site, while the instances executing in the backup site are used in a standby state. On identifying that a disaster has occurred, the user requests received immediately after identification of the disaster are processed using only the instances executing in the backup site. The cluster at the backup site is then scaled out to add application instances until a desired level/percentage is achieved.

Abstract: An aspect of the present invention mitigates reduction in availability level during maintenance of nodes in a cluster. In one embodiment, on receiving an indication that a maintenance activity is to be performed on the cluster, a scaling out of the cluster is first performed to add some nodes having the maintenance activity already performed, followed by a scaling in of the cluster to remove some of the nodes in the cluster which do not yet have the maintenance activity performed. The scaling out is performed before any scaling in of the cluster such that the number of nodes available in the cluster after the scaling in is not less than the number of nodes in the cluster at the time of receiving the indication. Accordingly, the reduction in availability level (which is based on the number of nodes available) is mitigated.

Abstract: Reducing access time for data in a file system when seek requests are received ahead of access requests. In one embodiment, an operating system providing access to the file system receives a seek request (from a user application) indicating an identifier of a file and a location within the file at which a data is sought to be accessed. In response, the operating system computes the offset of a disk block containing the location (thereby the data that is sought to be accessed). On receiving an access request (after the seek request from the same user application) indicating an operation to be performed on the data, the operating system executes the operation on the data using the pre-computed offset of the disk block. The computation of the disk block is performed before the access request is received thereby reducing the time required to process the access request.

Abstract: A method for managing load in a network comprising a first set of hosts, a second set of hosts and a centralized server is provided. A virtual machine runs on each of the first set of hosts. The centralized server receives resource donation information from each of the second set of hosts that are underutilized. Further, a load surge indicating additional tasks to be performed by the first set of hosts and the second set of hosts is identified. Next, the centralized server negotiates with the second set of hosts for modification of the resource donation information. Thereafter, one or more hosts are determined, based on the resource donation information and the load surge. These hosts create a virtual machine, based on the resource donation information, and become a part of the first set of hosts. The centralized server delegates the additional tasks among the first set of hosts.

Abstract: Virtual machines can be pre-created in a grid environment. Pre-created machines can be of a tiny configuration to avoid consuming resources. A request for a virtual machine in the grid can be granted by ballooning a pre-created tiny virtual machine to a larger configuration. The tiny pre-created virtual machine can be advertised as being of a non-tiny configuration. Agents can work in concert to coordinate handing requests for a virtual machine in the grid. The virtual machine can be initialized before it is reduced to a tiny configuration. Ballooning the virtual machine can take considerably less time than creating it from scratch. Thus, high performance computing can be provided on virtual machines in a grid environment, enabling virtual machine technology to be applied in a wide variety of grid-based scenarios.

Abstract: A method and system for extracting data of a buffer after a failure of an operating system. An application is registered prior to the failure. The registering includes identifying a buffer in which the data to be extracted is stored prior to the failure. The buffer is reserved to maintain the data residing in the buffer as unchanged from initiation to completion of a fast reboot of the operating system. The fast reboot is responsive to the failure. An in-memory file is generated during the fast reboot, points to the data residing in the buffer, and is stored in volatile memory and not in persistent storage. The data is extracted via an instruction which is executed by the application after completion of the fast reboot, and which operates on the in-memory file.

Abstract: The automatic selection of an input/output scheduler in a computing system with a plurality of input/output schedulers is disclosed. Each of the plurality of input/output schedulers is mapped against a corresponding desired set of heuristics. Heuristics relating to job requests submitted by processes in the computer system are monitored and analysed. These heuristics may include the number of read and write requests, the ratio of read requests to write requests, input/output throughput, disk utilization and the average time taken for processes to submit subsequent jobs once an initial job completes. The analysed heuristics are compared to the desired sets of heuristics for the plurality of input/output schedulers to select one of the plurality of input/output schedulers.

Abstract: The automatic selection of an input/output scheduler in a computing system with a plurality of input/output schedulers is disclosed. Each of the plurality of input/output schedulers is mapped against a corresponding desired set of heuristics. Heuristics relating to job requests submitted by processes in the computer system are monitored and analysed. These heuristics may include the number of read and write requests, the ratio of read requests to write requests, input/output throughput, disk utilization and the average time taken for processes to submit subsequent jobs once an initial job completes. The analysed heuristics are compared to the desired sets of heuristics for the plurality of input/output schedulers to select one of the plurality of input/output schedulers.