Abstract: Aspects of the present invention provide devices that determine a load for each tenant of a plurality of tenants running applications on a shared computer server for a predetermined interval of time, wherein the computer server includes a plurality of computer processor cores, compute a capacity for each tenant of the plurality of tenants which includes a difference between the load and a service level agreement for each tenant, determine computer processor cores corresponding to the capacity of a largest capacity tenant, wherein the processors cores include a subset of the plurality of computer processor cores for the shared computer server, pin the subset of computer processor cores to perform garbage collection for one or more tenants, and invoke the garbage collection using the pinned subset of computer processor cores which deallocates no longer used memory in a corresponding heap for the one or more tenants.

Abstract: Aspects provide multi-tier data synchronization based on a concurrent linked monitor list. A computer processor associates each of different data regions of a packed data object with different mutual exclusion monitor nodes of a linked list, the data regions defined by a data offset location within memory data and a length of the data region from the offset. In response to determining that a first data region of the packed data object is on-heap memory, the processor associates the first data region with a container representative of the linked list sorted in ascending order of the respective offset values, and a hash code of the container; and in response to determining that a second data region of the packed data object is off-heap memory, stores container information for the second data region in the linked list and resorts the linked-list nodes of container information in ascending order of offset values.

Abstract: Aspects of the present invention provide devices that determine a load for each tenant of a plurality of tenants running applications on a shared computer server for a predetermined interval of time, wherein the computer server includes a plurality of computer processor cores, compute a capacity for each tenant of the plurality of tenants which includes a difference between the load and a service level agreement for each tenant, determine computer processor cores corresponding to the capacity of a largest capacity tenant, wherein the processors cores include a subset of the plurality of computer processor cores for the shared computer server, pin the subset of computer processor cores to perform garbage collection for one or more tenants, and invoke the garbage collection using the pinned subset of computer processor cores which deallocates no longer used memory in a corresponding heap for the one or more tenants.

Abstract: A first execution of an application is performed on a virtual machine. A set of virtual machine parameters associated with the first execution is determined. One or more command lines of the application are mapped to the set of virtual machine parameters. The mapping is stored in a cache. A second execution of the application is performed on the virtual machine. The second execution retrieves the set of virtual machine parameters from the cache.

Abstract: A first execution of an application is performed on a virtual machine. A set of virtual machine parameters associated with the first execution is determined. One or more command lines of the application are mapped to the set of virtual machine parameters. The mapping is stored in a cache. A second execution of the application is performed on the virtual machine. The second execution retrieves the set of virtual machine parameters from the cache.

Abstract: Embodiments disclose systems, methods and computer program products to perform an operation for sharing artifacts between instances of an application deployed in a cloud computing environment. The operation generally includes upon determining, during staging of the application, that a set of artifacts are not available for instances of the application to share in the cloud computing environment, generating the set of artifacts via a first application instance, storing the set of artifacts, and requesting a re-staging of the application. The operation also includes during the re-staging of the application, generating a file for deploying scaled instances of the application and packing the stored set of artifacts into the generated file via a second application instance. The operation further includes executing an instance scale out of the application with the generated file comprising the stored set of artifacts.

Abstract: A first execution of an application is performed on a virtual machine. A set of virtual machine parameters associated with the first execution is determined. One or more command lines of the application are mapped to the set of virtual machine parameters. The mapping is stored in a cache. A second execution of the application is performed on the virtual machine. The second execution retrieves the set of virtual machine parameters from the cache.

Abstract: A first execution of an application is performed on a virtual machine. A set of virtual machine parameters associated with the first execution is determined. One or more command lines of the application are mapped to the set of virtual machine parameters. The mapping is stored in a cache. A second execution of the application is performed on the virtual machine. The second execution retrieves the set of virtual machine parameters from the cache.

Abstract: Aspects provide multi-tier data synchronization based on a concurrent linked monitor list. A computer processor associates each of different data regions of a packed data object with different mutual exclusion monitor nodes of a linked list, the data regions defined by a data offset location within memory data and a length of the data region from the offset. In response to determining that a first data region of the packed data object is on-heap memory, the processor associates the first data region with a container representative of the linked list sorted in ascending order of the respective offset values, and a hash code of the container; and in response to determining that a second data region of the packed data object is off-heap memory, stores container information for the second data region in the linked list and resorts the linked-list nodes of container information in ascending order of offset values.

Abstract: Aspects provide multi-tier data synchronization based on a concurrent linked monitor list. A computer processor associates each of different data regions of a packed data object with different mutual exclusion monitor nodes of a linked list, the data regions defined by a data offset location within memory data and a length of the data region from the offset. In response to determining that a first data region of the packed data object is on-heap memory, the processor associates the first data region with a container representative of the linked list sorted in ascending order of the respective offset values, and a hash code of the container; and in response to determining that a second data region of the packed data object is off-heap memory, stores container information for the second data region in the linked list and resorts the linked-list nodes of container information in ascending order of offset values.

Abstract: Aspects provide multi-tier data synchronization based on a concurrent linked monitor list. A computer processor associates each of different data regions of a packed data object with different mutual exclusion monitor nodes of a linked list, the data regions defined by a data offset location within memory data and a length of the data region from the offset. In response to determining that a first data region of the packed data object is on-heap memory, the processor associates the first data region with a container representative of the linked list sorted in ascending order of the respective offset values, and a hash code of the container; and in response to determining that a second data region of the packed data object is off-heap memory, stores container information for the second data region in the linked list and resorts the linked-list nodes of container information in ascending order of offset values.

Abstract: Embodiments disclose systems, methods and computer program products to perform an operation for sharing artifacts between instances of an application deployed in a cloud computing environment. The operation generally includes upon determining, during staging of the application, that a set of artifacts are not available for instances of the application to share in the cloud computing environment, generating the set of artifacts via a first application instance, storing the set of artifacts, and requesting a re-staging of the application. The operation also includes during the re-staging of the application, generating a file for deploying scaled instances of the application and packing the stored set of artifacts into the generated file via a second application instance. The operation further includes executing an instance scale out of the application with the generated file comprising the stored set of artifacts.