Abstract: A system, a computer readable storage medium, and a method for determining a suggested component restart order in a computer system on a basis of one or more heuristic analyses of a plurality of input data. The method can include performing one or more sort or merge orders after one or more of each heuristic analysis, combining the one or more sort orders according to a weighting algorithm, generating a recovery dependency graph between each of the components of the computer system, and presenting the recovery dependency graph.

Abstract: Methods, systems, and computer program products for providing fault injection to Cloud-provisioned machines are provided herein. A method includes determining one or more fault conditions to be associated with a fault injection implementation based on one or more parameters associated with a request for the fault injection implementation; generating a specification for a lifecycle of the fault injection implementation based on the one or more fault conditions; and executing the fault injection implementation in a target system, wherein said executing comprises effecting the lifecycle of the fault injection implementation according to the generated specification.

Abstract: A mechanism is provided for identifying patterns of a set of software applications instances from their documents. The computer-implemented method begins with constructing different attribute vector types using a knowledge ontology. The knowledge ontology captures semantics based on keywords associated with resource attributes derived from one or more documents related to at least a portion of these software application instances. A knowledge base is built from the attribute vector types and the documents of these application instances. These are merged into the knowledge base with the knowledge base previously built from previous software application instances. Analytics are performed on the knowledge base to identify at least one of common patterns of deployments, configurations, or other attribute vector types, or a combination thereof.

Abstract: Methods, systems, and computer program products for black box techniques for detecting performance and availability issues in virtual machines exploiting hardware assisted virtualization are provided herein. A computer-implemented method includes capturing multiple hardware assisted virtualization exit calls generated in connection with a given virtual machine; calculating one or more virtual machine performance metrics attributed to the given virtual machine based on the multiple hardware assisted virtualization exit calls; determining one or more virtual machine performance issues and/or one or more virtual machine availability issues attributed to the given virtual machine based on the one or more calculated virtual machine performance metrics; and outputting an alert identifying the one or more determined virtual machine performance issues and/or the one or more virtual machine availability issues attributed to the given virtual machine.

Abstract: Methods, systems, and computer program products for storage system-based replication for disaster recovery in virtualized environments are provided herein.

Abstract: Determining which snapshot deltas tend to occur in: (i) healthy virtual machines (VMs) that have been subject to an attack yet remained healthy, and/or (ii) unhealthy VMs that have apparently been adversely affected by an attack. Snapshot deltas that occur in at least some (or more preferably all) of the healthy VM subset provide information about software changes (for example, updates, configuration changes) that may be helpful. Snapshot deltas that occur in at least some (or more preferably all) of the unhealthy VM subsets provide information about software changes (for example, updates, configuration changes) that may be unhelpful.

Abstract: Techniques for model-based analysis of a data center. A method includes creating a metamodel based on domain knowledge to represent a type of object and/or relationship of a data center, using static and dynamic configuration and data analysis techniques to discover topology of elements of the data center and represent the topology as a model that is an instance of the metamodel, extending the metamodel, using the model to perform analysis of the data center in connection with a specified task, leveraging domain knowledge represented in nodes of the extended metamodel to guide the analysis in terms of determining guidelines to apply to each node and determining relationships to traverse to continue the analysis, extending the domain knowledge by updating the extended metamodel upon discovery of additional knowledge for use in improving analysis tasks, and extending the model on-demand using dynamic analysis techniques upon detection of multiple analysis failures.

Abstract: Determining which snapshot deltas tend to occur in: (i) healthy virtual machines (VMs) that have been subject to an attack yet remained healthy, and/or (ii) unhealthy VMs that have apparently been adversely affected by an attack. Snapshot deltas that occur in at least some (or more preferably all) of the healthy VM subset provide information about software changes (for example, updates, configuration changes) that may be helpful. Snapshot deltas that occur in at least some (or more preferably all) of the unhealthy VM subsets provide information about software changes (for example, updates, configuration changes) that may be unhelpful.

Abstract: Methods, systems, and computer program products for providing fault injection to Cloud-provisioned machines are provided herein. A method includes determining one or more fault conditions to be associated with a fault injection implementation based on one or more parameters associated with a request for the fault injection implementation; generating a specification for a lifecycle of the fault injection implementation based on the one or more fault conditions; and executing the fault injection implementation in a target system, wherein said executing comprises effecting the lifecycle of the fault injection implementation according to the generated specification.

Abstract: A base query having a plurality of base query terms is obtained. A plurality of problem log files are accessed. Words, contained in a corpus vocabulary, are extracted from the plurality of problem log files. Based on the words extracted from the plurality of problem log files, a first expanded query is generated from the base query. The corpus is queried, via a query engine and a corpus index, with a second expanded query related to the first expanded query.

Abstract: Determining which snapshot deltas tend to occur in: (i) healthy virtual machines (VMs) that have been subject to an attack yet remained healthy, and/or (ii) unhealthy VMs that have apparently been adversely affected by an attack. Snapshot deltas that occur in at least some (or more preferably all) of the healthy VM subset provide information about software changes (for example, updates, configuration changes) that may be helpful. Snapshot deltas that occur in at least some (or more preferably all) of the unhealthy VM subsets provide information about software changes (for example, updates, configuration changes) that may be unhelpful.

Abstract: For disaster recovery involving a first site and a disaster recovery site, where at least a portion of management service metadata not isolated within the management service, a failover process is initiated, including creating an initial snapshot of the distributed metadata state. In a failback process, a representation is created of state changes for the management service and a delta description is calculated therefrom. The delta description is transmitted to the first site; and a reverse replica is created, at the first site, of all the workload components from the disaster recovery site. The delta description is played back to restore a distributed metadata state that existed in the disaster recovery site and to re-create it in the first site.

Abstract: For disaster recovery involving a first site and a disaster recovery site, where at least a portion of management service metadata not isolated within the management service, a failover process is initiated, including creating an initial snapshot of the distributed metadata state. In a failback process, a representation is created of state changes for the management service and a delta description is calculated therefrom. The delta description is transmitted to the first site; and a reverse replica is created, at the first site, of all the workload components from the disaster recovery site. The delta description is played back to restore a distributed metadata state that existed in the disaster recovery site and to re-create it in the first site.

Abstract: During normal operation, at a first site, of a disaster recovery management unit, at least one customer workload machine, at least one management service machine, and metadata for the at least one management service machine are replicated to a remote disaster recovery site. After a disaster at the first site, a replicated version of the at least one customer workload machine and a replicated version of the at least one management service machine are brought up at the remote disaster recovery site. A replicated version of the metadata for the at least one management service machine is reconfigured by executing, on the replicated version of the at least one management service machine, a failover script, to obtain reconfigured replicated metadata for the replicated version of the at least one management service machine. When the first site comes back up, failback is carried out, essentially in the reverse order.

Abstract: A method for creating a workflow using system administrator actions to resolve a system issue is provided. The method may include assigning a ticket to a category. The method may include capturing a first snapshot of a first system state of a machine before a system administrator begins a corrective action. The method may include capturing a second snapshot of a second system state of the machine after system administrator corrective action. The method may include creating a difference set based on a comparison of the first snapshot and the second snapshot. The method may include generating summaries of administrator action. The method may include dividing the summaries into groups of summaries. The method may include constructing a candidate workflow for each group. The method may include presenting the candidate workflow to a subject matter expert. The method may include storing the reviewed candidate workflow in a repository.

Abstract: Methods, systems, and articles of manufacture for selected VM replication and VM restart techniques are provided herein. A method includes selecting a sub-set of one or more VMs from a set of multiple VMs in a system to be replicated before an identification of one or more failed VMs in the set of multiple VMs; replicating the sub-set of one or more VMs before the identification of one or more failed VMs in the set of multiple VMs; selecting a sub-set of the identified one or more failed VMs to be restarted upon an identification of the one or more failed VMs in the set of multiple VMs in the system; and restarting the sub-set of the identified one or more failed VMs upon the identification of the one or more failed virtual machines in the set of multiple VMs.

Abstract: A method, system, and computer program product are disclosed for merging search results. In one embodiment, the method comprises identifying a query, splitting the query into sub-queries, and calculating information content for each of the sub-queries. This method also comprises executing each of the sub-queries to obtain a plurality of search results, and combining the search results based on the information content calculated for the sub-queries. In an embodiment, the execution of each of the sub-queries includes identifying a multitude of search results for at least one of the sub-queries; and the combining includes grouping said multitude of search results into a plurality of clusters, and computing a relevance score for each of said clusters. In the embodiment the combining further includes merging the clusters based on the relevance scores computed for the clusters as well as the information content calculated for the sub-queries.

Abstract: During normal operation, at a first site, of a disaster recovery management unit, at least one customer workload machine, at least one management service machine, and metadata for the at least one management service machine are replicated to a remote disaster recovery site. After a disaster at the first site, a replicated version of the at least one customer workload machine and a replicated version of the at least one management service machine are brought up at the remote disaster recovery site. A replicated version of the metadata for the at least one management service machine is reconfigured by executing, on the replicated version of the at least one management service machine, a failover script, to obtain reconfigured replicated metadata for the replicated version of the at least one management service machine. When the first site comes back up, failback is carried out, essentially in the reverse order.

Abstract: A method, system, and computer program product are disclosed for merging search results. In one embodiment, the method comprises identifying a query, splitting the query into sub-queries, and calculating information content for each of the sub-queries. This method also comprises executing each of the sub-queries to obtain a plurality of search results, and combining the search results based on the information content calculated for the sub-queries. In an embodiment, the execution of each of the sub-queries includes identifying a multitude of search results for at least one of the sub-queries; and the combining includes grouping said multitude of search results into a plurality of clusters, and computing a relevance score for each of said clusters. In the embodiment the combining further includes merging the clusters based on the relevance scores computed for the clusters as well as the information content calculated for the sub-queries.

Abstract: User trustworthiness may be introduced in implicit feedback based supervised machine learning systems. A set of training data examples may be scored based on the trustworthiness of users associated respectively with the training data examples. The training data examples may be sampled into a plurality of training data sets based on a weighted bootstrap sampling technique, where each weight is a probability proportional to trustworthiness score associated with an example. A machine learning algorithm takes the plurality of the training data sets as input and generates a plurality of trained models. Outputs from the plurality of trained models may be ensembled by computing a weighted average of the outputs of the plurality of trained models.