Abstract: A method of reducing power consumption of a server cluster of host systems with virtual machines executing on the host systems is disclosed. The method includes recommending host system power-on when there is a host system whose utilization is above a target utilization, and recommending host system power-off when there is a host system whose utilization is below the target utilization. Recommending host system power-on includes calculating impact of powering on a standby host system with respect to reducing the number of highly-utilized host systems in the server cluster. The impact of powering on is calculated by simulating moving some virtual machines from highly utilized host systems to the standby host system being recommended to be powered on. Recommending host system power-off includes calculating impact of powering off a host system with respect to decreasing the number of less-utilized host systems in the server cluster.

Abstract: A method, and associated apparatus, comprises calculating a first part of a message authentication function by a first processor, calculating a second part of the message authentication function by a second processor, and combining the first and second parts into the message authentication function by the first or second processor. The message authentication function can be used to authenticate data transmitted between the first processor and a third processor.

Abstract: A primary copy of data is held at a primary storage facility, while data that is redundant of the primary copy is held at a secondary storage facility. To inhibit propagation of errors from the primary copy to the redundant data, write transactions to the redundant data are queued at the second storage facility, until a specified time elapses or until a specified event occurs (or until combination hereof occurs). Write transactions may be collected in groups at the primary facility prior to forwarding to the secondary facility and may also be batched at the secondary facility prior to being applied to the redundant data. Overwrites may be allowed within a group at the primary facility to conserve communication bandwidth between the primary and secondary storage facilities. Overwrites may be allowed within a batch at the secondary facility to conserve space occupied by the transactions at the secondary facility.

Abstract: A method for taking snapshots of data. In an embodiment, a first map data structure is obtained that records locations for a plurality of data blocks. A second map data structure is formed that is initially empty of locations, the second map data structure representing the snapshot after the snapshot is started. Writes on data that arrive before the snapshot starts are applied to the first map, and writes that arrive after the snapshot starts are applied to the second map.

Abstract: A sequence of write transactions are performed at a first storage facility. The write transactions are arranged into a sequence of send batches forwarded to a second storage facility where the write transactions are arranged into a sequence of receive batches. At the first storage facility or at the second storage facility, a first write transaction is replaced with a second write transaction wherein the second write transaction overwrites data written by the first write transaction. A receive batch includes all write transactions between the first write transaction and the second write transaction. The write transactions are applied to a redundant data copy at the second storage facility in which all of the write transactions for the receive batch are applied as a whole to the redundant copy of the data.

Abstract: Methods and apparatus for obtaining consistency of redundant data after a failover event. In one aspect, a redundant data storage system has a first data storage facility that initially acts as a primary facility for storage requests and a second data storage facility that initially acts as a secondary facility for the storage requests. The second data storage facility is conditioned to assume the role of the primary facility in response to a failover event. The first data storage facility is conditioned to assume the role of the secondary facility, which includes sending a copy of data committed at the second data storage facility to the first data storage facility. The copy of data includes a version of data committed at the second storage facility.

Abstract: Techniques for performing data redundancy operations in a distributed manner. A primary data storage facility stores a primary copy of data and a secondary facility stores data that is redundant of the primary copy of the data. The primary facility includes a first redundancy appliance that receives a first sequence of write requests and stores data for the first sequence of write requests in mass storage associated with the first redundancy appliance. A second redundancy appliance receives a second sequence of write requests and stores data for the second sequence of write requests in mass storage associated with the second redundancy appliance. Thus, a workload is shared among the first and second redundancy appliances by dividing the workload into the first and second sequences of write requests, where each sequence is handled by a different redundancy appliance.

Abstract: Techniques for performing data redundancy operations in a fault-tolerant manner. In one aspect, a primary data storage facility stores a primary copy of data and a secondary facility stores data that is redundant of the primary copy of the data. The primary facility includes a first redundancy appliance that receives a sequence of write requests and stores data for the sequence of write requests in storage associated with the primary storage facility. A second redundancy appliance shadows the first redundancy appliance and assumes the role of the first redundancy appliance in the event of a fault at the first redundancy appliance. In this way, fault tolerance is increased by the presence of the second, shadow appliance.

Abstract: A technique for adaptive batching for asynchronous data redundancy. A sequence of write transactions are adaptively arranged into a sequence of send batches at the first storage facility. The transactions are received at a second storage facility and applied to a redundant data copy at the second storage facility. The second storage facility may arrange the write transactions according to a sequence of receive batches. The batch sizes may be adaptively adjusted or completed. The batch sizes or adaptive completion of the batches may be based on, for example, availability of a communication medium between the first storage facility and the second storage facility. Each send batch may be forwarded to the second storage facility upon completion.

Abstract: A state machine and system for redundantly backing up data. A first storage facility is controlled by a first state machine having a finite number of states, each state having a set of allowed operations. The first state machine includes at least one state for controlling the first storage facility to operate as a primary storage facility for storing and updating a primary copy of the data. A second storage facility is controlled by a second state-machine that has least one state for controlling the second storage facility to operate as a secondary storage facility for storing redundant data. The second state machine also has at least one state for controlling the second storage facility to operate as the primary storage facility. The second storage facility assumes the role of primary in response to a fault at the first storage facility or based on the origin of request traffic.

Abstract: A method for taking snapshots of data. In an embodiment, a first map data structure is obtained that records locations for a plurality of data blocks. A second map data structure is formed that is initially empty of locations, the second map data structure representing the snapshot after the snapshot is started. Writes on data that arrive before the snapshot starts are applied to the first map, and writes that arrive after the snapshot starts are applied to the second map.

Abstract: An embodiment of a method of routing a packet between nodes of a network begins with a step of determining that a route of an external network from a source node to a network node provides an expected near minimum transmission time for transmission of the packet from the source node to a destination node. The method continues with a step of determining that a packet queue for a network link at a source node exceeds a threshold. The method concludes with a step of routing the packet to the destination node via the external network and the network node.

Abstract: A method of redundantly storing data in a geographically-diverse data-storing system is presented. The data-storing system has one or more data sites and a set of data-protecting sites. A new version of a set of data is written to a first data site, and a representation of the new version is generated. The representation is transmitted from the first data site to a subset of the data-protecting sites. At each data-protecting site, the representation is stored and an acknowledgment of the storing is transmitted back. Also, upon receipt back of a commit command, a data-protecting operation is performed on the representation to generate a data-protecting value, which is also stored. Then, storage corresponding to the representation is released. Further, at a first data site, once acknowledgments from each data-protecting site are received, a commit command is transmitted to the subset of data-protecting sites. Additionally, storage is released corresponding to a previous version of the set of data.

Abstract: A method, and associated apparatus, comprises calculating a first part of a message authentication function by a first processor, calculating a second part of the message authentication function by a second processor, and combining the first and second parts into the message authentication function by the first or second processor. The message authentication function can be used to authenticate data transmitted between the first processor and a third processor.

Abstract: A method for managing traffic flow through a multipath network and systems and apparatuses configured to employ such a method are provided. The method includes forwarding a packet along a first link of the multipath network and tracking a load of the first link subsequent to forwarding the packet. In addition, the method includes preserving the first link for a subsequent packet having the same flow address as the forwarded packet upon determining a desired load change of the first link is less than a predetermined value.

Abstract: Techniques for performing data redundancy operations in a distributed manner. A primary data storage facility stores a primary copy of data and a secondary facility stores data that is redundant of the primary copy of the data. The primary facility includes a first redundancy appliance that receives a first sequence of write requests and stores data for the first sequence of write requests in mass storage associated with the first redundancy appliance. A second redundancy appliance receives a second sequence of write requests and stores data for the second sequence of write requests in mass storage associated with the second redundancy appliance. Thus, a workload is shared among the first and second redundancy appliances by dividing the workload into the first and second sequences of write requests, where each sequence is handled by a different redundancy appliance.

Abstract: A technique for adaptive batching for asynchronous data redundancy. A sequence of write transactions are adaptively arranged into a sequence of send batches at the first storage facility. The transactions are received at a second storage facility and applied to a redundant data copy at the second storage facility. The second storage facility may arrange the write transactions according to a sequence of receive batches. The batch sizes may be adaptively adjusted or completed. The batch sizes or adaptive completion of the batches may be based on, for example, availability of a communication medium between the first storage facility and the second storage facility. Each send batch may be forwarded to the second storage facility upon completion.

Abstract: Methods and apparatus for obtaining consistency of redundant data after a failover event. In one aspect, a redundant data storage system has a first data storage facility that initially acts as a primary facility for storage requests and a second data storage facility that initially acts as a secondary facility for the storage requests. The second data storage facility is conditioned to assume the role of the primary facility in response to a failover event. The first data storage facility is conditioned to assume the role of the secondary facility, which includes sending a copy of data committed at the second data storage facility to the first data storage facility. The copy of data includes a version of data committed at the second storage facility.

Abstract: Techniques for performing data redundancy operations in a fault-tolerant manner. In one aspect, a primary data storage facility stores a primary copy of data and a secondary facility stores data that is redundant of the primary copy of the data. The primary facility includes a first redundancy appliance that receives a sequence of write requests and stores data for the sequence of write requests in storage associated with the primary storage facility. A second redundancy appliance shadows the first redundancy appliance and assumes the role of the first redundancy appliance in the event of a fault at the first redundancy appliance. In this way, fault tolerance is increased by the presence of the second, shadow appliance.

Abstract: Techniques for performing data redundancy operations using a portal and a host computer. In one aspect, a primary data storage facility stores a primary copy of data and a secondary facility stores data that is redundant of the primary copy of the data. The primary facility includes a host computer having a first redundancy component for storing data for a sequence of write requests in storage associated with the primary storage facility and a first redundancy portal for retrieving the data and for forwarding the data to the secondary storage facility. The first redundancy portal is outside a communication path between the host computer and the storage. This prevents the redundancy portal from becoming a communication bottleneck. A second redundancy portal may be provided at the secondary facility.