Abstract: Techniques are described for placing virtual machines (VM) on computer hosts. In one embodiment, a user may compose a constraint specification document which includes VM and host properties and how they are retrieved, as well as constraint predicates that define valid VM placements on hosts. Use of the constraint specification document permits new constraints, including constraints that involve new properties, to be handled without requiring changing the underlying code for collecting required input data and processing said data to determine whether placement constraints are satisfied. Instead, based on the constraint specification document, a resource scheduler or high availability module may program a programmable data collector to fetch the needed properties from the appropriate places.

Abstract: Methods and systems to reconfigure clusters in elastic multi-tenant cloud computing system. An example method includes partitioning a first resource reservation of a first virtual data center between a first cluster and a second cluster and partitioning a second resource reservation of a second virtual data center between the first cluster and the second cluster, and based on the partitioning of the first resource reservation and the second resource reservation, collectively adjusting a first portion of the first resource reservation allotted to the first cluster and a second portion of the second resource reservation allotted to the first cluster in a same reconfiguration operation.

Abstract: Embodiments maintain high availability of software application instances in a fault domain. Subordinate hosts are monitored by a master host. The subordinate hosts publish heartbeats via a network and datastores. Based at least in part on the published heartbeats, the master host determines the status of each subordinate host, distinguishing between subordinate hosts that are entirely inoperative and subordinate hosts that are operative but partitioned (e.g., unreachable via the network). The master host may restart software application instances, such as virtual machines, that are executed by inoperative subordinate hosts or that cease executing on partitioned subordinate hosts.

Abstract: A system and method for performing resource allocation for a host computer cluster uses a copy of a cluster resource allocation hierarchy of the host computer cluster to generate a host resource allocation hierarchy of a host computer in the host computer cluster.

Abstract: In one embodiment, a method for placing virtual machines in a collection is provided. A plurality of equivalence sets of hosts is determined prior to placing virtual machines in the collection. The hosts in an equivalence set of hosts are considered similar. An equivalence set of hosts in the plurality of equivalence sets is selected to place the virtual machines in the collection. The method then places at least a portion of the virtual machines in the collection on one or more hosts in the selected equivalence set of hosts.

Abstract: Recovery of virtual machines when one or more hosts fail includes identifying virtual machines running on the remaining functioning hosts. Some of the identified powered on virtual machines are suspended in favor of restarting some of the failed virtual machines from the failed host(s). A subsequent round of identifying virtual machines for suspension and virtual machines for restarting is performed. Virtual machines for suspension and restarting may be identified based on their associated “recovery time objective” (RTO) values or their “maximum number of RTO violations” value.

Abstract: Techniques are described for placing virtual machines (VM) on computer hosts. In one embodiment, a user may compose a constraint specification document which includes VM and host properties and how they are retrieved, as well as constraint predicates that define valid VM placements on hosts. Use of the constraint specification document permits new constraints, including constraints that involve new properties, to be handled without requiring changing the underlying code for collecting required input data and processing said data to determine whether placement constraints are satisfied. Instead, based on the constraint specification document, a resource scheduler or high availability module may program a programmable data collector to fetch the needed properties from the appropriate places.

Abstract: In one embodiment, a method determines a first set of virtual machines and a second set of virtual machines. The first set of virtual machines is associated with a first priority level and the second set of virtual machines is associated with a second priority level. A first set of computing resources and a second set of computing resources are associated with hosts. Upon determining a failure of a host, the method performs: generating a power off request for one or more of the second set of virtual machines powered on the second set of computing resources and generating a power on request for one or more virtual machines from the first set of virtual machines that were powered on the failed host, the power on request powering on the one or more virtual machines from the first set of virtual machines on the second set of computing resources.

Abstract: A system and method for performing resource allocation for a host computer cluster uses a copy of a cluster resource allocation hierarchy of the host computer cluster to generate a host resource allocation hierarchy of a host computer in the host computer cluster.

Abstract: Embodiments maintain high availability of software application instances in a fault domain. Subordinate hosts are monitored by a master host. The subordinate hosts publish heartbeats via a network and datastores. Based at least in part on the published heartbeats, the master host determines the status of each subordinate host, distinguishing between subordinate hosts that are entirely inoperative and subordinate hosts that are operative but partitioned (e.g., unreachable via the network). The master host may restart software application instances, such as virtual machines, that are executed by inoperative subordinate hosts or that cease executing on partitioned subordinate hosts.

Abstract: A method for restarting a virtual machine in a virtual computing system having a plurality of hosts and a resource scheduler for the plurality of hosts includes writing a placement request for the virtual machine to a shared channel that is accessible by the resource scheduler. The method further includes reading a placement result from the shared channel, wherein the placement result is generated by the resource scheduler responsive to the placement request; and restarting the virtual machine in accordance with the placement result.

Abstract: Embodiments maintain high availability of software application instances in a fault domain. Subordinate hosts are monitored by a master host. The subordinate hosts publish heartbeats via a network and datastores. Based at least in part on the published heartbeats, the master host determines the status of each subordinate host, distinguishing between subordinate hosts that are entirely inoperative and subordinate hosts that are operative but partitioned (e.g., unreachable via the network). The master host may restart software application instances, such as virtual machines, that are executed by inoperative subordinate hosts or that cease executing on partitioned subordinate hosts.

Abstract: Recovery of virtual machines when one or more hosts fail includes identifying virtual machines running on the remaining functioning hosts. Some of the identified powered on virtual machines are suspended in favor of restarting some of the failed virtual machines from the failed host(s). A subsequent round of identifying virtual machines for suspension and virtual machines for restarting is performed. Virtual machines for suspension and restarting may be identified based on their associated “recovery time objective” (RTO) values or their “maximum number of RTO violations” value.

Abstract: In one embodiment, a method for placing virtual machines in a collection is provided. A plurality of equivalence sets of hosts is determined prior to placing virtual machines in the collection. The hosts in an equivalence set of hosts are considered similar. An equivalence set of hosts in the plurality of equivalence sets is selected to place the virtual machines in the collection. The method then places at least a portion of the virtual machines in the collection on one or more hosts in the selected equivalence set of hosts.

Abstract: Methods and systems to reconfigure clusters in elastic multi-tenant cloud computing system. An example method includes partitioning a first resource reservation of a first virtual data center between a first cluster and a second cluster and partitioning a second resource reservation of a second virtual data center between the first cluster and the second cluster, and based on the partitioning of the first resource reservation and the second resource reservation, collectively adjusting a first portion of the first resource reservation allotted to the first cluster and a second portion of the second resource reservation allotted to the first cluster in a same reconfiguration operation.

Abstract: In one embodiment, a method for placing virtual machines in a collection is provided. A plurality of equivalence sets of compatible hosts is determined prior to placing virtual machines in the collection. The hosts in an equivalence set of hosts are considered similar. An equivalence set of hosts in the plurality of equivalence sets is selected to place the virtual machines in the collection. The method then places at least a portion of the virtual machines in the collection on one or more hosts in the selected equivalence set of hosts.

Abstract: In one embodiment, a method includes determining an instrumentation action to perform with the software program when a logging statement is encountered during execution of a software program. The instrumentation action is performed by an instrumentation service associated with a logging service and the execution of the software program is monitored based on the instrumentation action being performed.

Abstract: In one embodiment, a method determines a first set of virtual machines and a second set of virtual machines. The first set of virtual machines is associated with a first priority level and the second set of virtual machines is associated with a second priority level. A first set of computing resources and a second set of computing resources are associated with hosts. Upon determining a failure of a host, the method performs: generating a power off request for one or more of the second set of virtual machines powered on the second set of computing resources and generating a power on request for one or more virtual machines from the first set of virtual machines that were powered on the failed host, the power on request powering on the one or more virtual machines from the first set of virtual machines on the second set of computing resources.

Abstract: In one embodiment, a method attempts, by a computing device, to determine a placement of a set of virtual machines on available hosts upon failure of a host. The placement considers the set of virtual machines as being not powered on any of the available hosts. The method further determines, by the computing device, a placed list of virtual machines in the set of virtual machines as a recommendation to power on to the available hosts. The determination of the placed list of virtual machines is used to determine a power off list of virtual machines in the set of virtual machines to power off, wherein virtual machines in the power off list of virtual machines are currently powered on available hosts but were considered to be powered off to determine the placement.

Abstract: In one embodiment, a method includes determining an instrumentation action to perform with the software program when a logging statement is encountered during execution of a software program. The instrumentation action is performed by an instrumentation service associated with a logging service and the execution of the software program is monitored based on the instrumentation action being performed.