Abstract: Systems and methods may be implemented to prevent application crashes by correlating a history of operating system (OS) updates with occurrence of past client application crashes using information that is crowd-sourced from multiple information handling systems so that action/s may be taken to prevent occurrence of future client application crashes on the information handling system/s. Machine learning (e.g., deep learning) may be employed to automatically correlate the history of OS updates with a record of past client application crashes that have occurred on multiple client information handling systems, and then the likely root cause/s for the client application crashes identified based on this correlation. These likely root cause/s may be corrected or otherwise addressed, e.g., by further investigation into the details of the root cause, and/or user or automatic system action to remove or block the root cause.

Abstract: A device may communicate with a server to obtain historical ticket data. The device may generate a data model, based on the historical ticket data. The device may communicate with a client device to obtain ticket data relating to an issue associated with a project. The device may classify, using the data model, the ticket data into a ticket type. The device may generate, using the data model and based on the ticket type, a set of recommended resolutions for resolving the issue associated with the project. The device may select, from the set of recommended resolutions, a particular resolution based on a set of selection criteria. The device may automatically perform one or more actions to implement the particular resolution to resolve the issue associated with the project.

Abstract: A memory controller includes, in one embodiment, a memory interface and a dynamic stripe length manager circuit configured to receive a first weighted health factor associated with a first memory block of the memory, determine a first collective stripe length of the first memory block based on the first weighted health factor, set a first number of zones in the first memory block based on the first collective stripe length, monitor the memory to detect a trigger event that triggers a calculation of a second collective stripe length of the first memory block, the second collective stripe length being larger than the first collective stripe length, receive a second weighted health factor associated with the first memory block, determine the second collective stripe length based on the second weighted health factor, and set a second number of zones in the first memory block based on the second collective stripe length.

Abstract: A framework for visualization based on healthcare guidelines is described herein. In accordance with one aspect, a decision graph is generated based on healthcare guidelines. The nodes of the decision graph are populated with patient records. The framework may perform data analytics on patient records associated with at least one of the nodes to generate results, and further generate a visualization of the results.

Abstract: In some examples, a method can include applying a respective label of a plurality of labels to a network device of a plurality of network devices on a network; determining a respective amount of a performance attribute over a period of time for each client device associated with the network devices; generating an implicit data heap structure of top N client devices across a plurality of distributed processes for each label of the plurality of labels; determining, based on an implicit data heap structure, a client device having the greatest amount of the performance attribute over the period of time for a label of the plurality of labels; and displaying a client identifier of the client device having the greatest amount of the performance attribute.

Abstract: A method for generating a prediction of a latency of a transaction processing system includes: sampling a first plurality of messages from a database that stores data indicative of messages previously processed by the transaction processing system including a characteristic and a processing time of each previously processed message; generating latency tables based upon the characteristics and the processing times of the sampled first plurality of messages; determining a characteristic of each of a second plurality of messages being processed by the transaction processing system; selecting, for each of the second plurality of messages, a latency table from the plurality of latency tables based upon the respective determined characteristic; simulating a processing time for each of the second plurality of messages based upon the respective selected latency table; and generating a latency prediction for the transaction processing system based upon the simulated processing times for the second plurality of message

Abstract: An apparatus and method are described for a multithreaded-aware performance monitor of a processor. For example, one embodiment of a processor comprises: one or more simultaneous multithreading cores to simultaneously execute multiple instruction threads; a plurality of performance monitor counters, each performance monitor counter to count baseline events during processing of the multiple instruction threads; and a performance monitor circuit to determine whether multiple threads are concurrently generating the same baseline event and, if so, then the performance monitor circuit to distribute the count of the baseline event for only one of the multiple threads in each processor cycle for which the multiple threads are active and the baseline event applies to.

Abstract: An apparatus and method are described for generating performance metrics of a processor. For example, one embodiment of a processor comprises: one or more simultaneous multithreading cores to simultaneously execute multiple instruction threads; a plurality of performance monitor counters, each to maintain a count of events occurring as a result of the execution of the multiple instruction threads; and a performance monitor unit to generate a plurality of performance metric values using the event counts stored in the performance monitor counters and in response to receipt of a request from software for the performance metric values.

Abstract: A method for invalidating a track of data on a storage drive in preparation to unpin the track is disclosed. In one embodiment, such a method includes invalidating certain metadata associated with a track of data residing on a storage drive of a storage system. The method further creates, in cache of the storage system, an invalid track image associated with the track. The method destages, from the cache, the invalid track image to the storage drive. Once the invalid track image is destaged, the method may unpin the track in cache, thereby enabling destages of the track from the cache to the storage drive going forward. A corresponding system and computer program product are also disclosed.

Abstract: A computing device for storing backups of virtual machines includes a persistent storage and a backup manager. The persistent storage stores backup policies. The backup manager identifies an end of a backup generation session for a virtual machine of the virtual machines and, in response to identifying the end of the backup generation session, identifies a continuity chain implicated by the backup generation session using the backup policies; performs a membership analysis of the identified continuity chain to identify a continuity state of the continuity chain; makes a first determination that the identified continuity chain is broken based on the identified continuity state; and, in response to the first determination, remediates the continuity chain.

Abstract: An agent for managing virtual machines includes a persistent storage and a processor. The persistent storage stores backup/restoration policies. The processor identify an end of a backup generation session for the virtual machines; make a first determination that the backup generation was a batch type backup session and, in response to the first determination, performs a batch level continuity analysis of backups generated via the backup generation session to identify a set of backup failures of the backup generation session; performs an unscheduled batch backup generation session based on the identified set of backup failures; and remediates the backup/restoration policies using the identified set of backup failures to ensure backup continuity of all backups associated with each of the virtual machines.

Abstract: Systems and methods are provided for controlling and monitoring a peripheral in an aircraft that includes a master module connected to each slave module. Each slave module is disposed around a controlled peripheral and is connected to a port of the master module by a bidirectional link. The master module sends data frames comprising the value of a counter. Each slave module reads the value of the counter included in the data frame received, updates a counter with the value read, checks whether the value of the updated counter corresponds to a time-period index associated with the slave module and if so transfers a data frame to the master module. The master module selects, from a table comprising time period indices and identifiers, the port connecting the master module to the slave module the identifier of which is associated with the time-period index that corresponds to the counter's value.

Abstract: A system management tool, with a risk assessment mode enabled, is executed within an execution infrastructure on a management computer system, to manage a target computer system in a production situation. When the execution of the tool reaches a risk segment which raises risk for the target system, a user is informed of at least one action to be executed in the risk segment. If the user agrees, the tool is allowed to execute in an automatic mode until an end of the risk segment is reached. Feedback is obtained from the user regarding safety of the risk segment; and the steps are repeated for a plurality of additional risk segments until the tool is deemed safe for all of the risk segments, after which the tool is transitioned from the risk assessment mode to an automatic mode of operation.

Abstract: A computing device includes an interface configured to interface and communicate with a dispersed storage network (DSN), a memory that stores operational instructions, and a processing module operably coupled to the interface and memory such that the processing module, when operable within the computing device based on the operational instructions, is configured to perform various operations. Based on a detected storage error, the computing device is configured to determine availability status of encoded data slices (EDSs) within a set of EDSs. When at least a threshold number of EDSs are available, the computing device is configured to initiate a rebuilding function to abate the detected storage error. When less than the threshold number of EDSs are available, the computing device is configured to initiate a slice repair function to at least one storage unit (SU) to abate the detected storage error.

Abstract: Approaches for monitoring performance in a networked environment are provided. An approach includes monitoring, using a first metric, performance of a first host running a virtual machine. The approach also includes determining, using a computer device, a second metric based on the virtual machine being migrated from the first host to a second host, wherein the second metric is a function of: (i) the first metric and (ii) a comparison of the first host and the second host. The approach further includes monitoring, using the second metric, performance of the second host running the virtual machine.

Abstract: Various embodiments are generally directed to techniques for network strengthening, such as by detecting issues with one or more network components and reconfiguring one or more upstream or downstream network components to preempt issues with the one or more upstream or downstream network components, for instance. Some embodiments are particularly directed to a tool (e.g., strengthening agent) that implements pre-scripted or dynamic hardening of up and downstream dependencies of a network component in response to an issue identified with the network component. In many embodiments, up and downstream components of a network component may be reconfigured while the issue with the network component is being addressed to preempt issues with the up and downstream components.

Abstract: The invention relates to a method for determining the position and shape of a control area on a road on which a vehicle is travelling, and to which a usage charge applies. According to the invention, a segment of the road is divided into segment sections and the perimeter of geographical coordinates of the control area associated with each segment section is calculated. At at least two different moments, a GNSS receiver calculates the position of the vehicle, said calculated positions being inside the control area; a control area being provided that is defined by a perimeter of geographical coordinates, fulfilling the requirements in terms of charging availability being above a pre-determined threshold value and the probability of a charging error being below a threshold value.

Abstract: A system and method for protecting entities of an availability zone include creating, by a policy engine associated with a virtual computing system, a protection policy definition for replicating a first set of entities of a first availability zone of the virtual computing system to a second availability zone of the virtual computing system. Each of the first set of entities is associated with a first common tag and the first set of entities are spread across first multiple clusters of the first availability zone. The system and method further include capturing, by the policy engine, a first plurality of snapshots of each of the first set of entities in the first availability zone in accordance with a first recovery point objective parameter and storing, by the policy engine, at least one copy of the first plurality of snapshots in the second availability zone.

Abstract: Policies can be applied to, and enforced for, specific resources by applying a corresponding tag to those resources. An entity, such as a customer of a resource provider, can generate one or more policies to be applied to a set of resources, where those policies can relate to data retention, backup, lifecycle events, and other such aspects. Each policy can be associated with a particular tag, which may comprise a key-value pair to be applied to various resources. A policy enforcement manager can determine the tagged resources and ensure that the relevant policies are applied. The policies can include logic or intelligence for performing a variety of tasks with respect to resources, groups of resources, or types of resources, as identified using the tags.

Abstract: Embodiments for automatic log collection of an automated data storage library by a processor. A snapshot of one or more error logs, service logs, accessor logs, and data logs is captured in the automated data storage library upon detection of an occurrence of a triggering event within the automated data storage library. The snapshot of the one or more logs in the automated data storage library is stored.

Abstract: A method, apparatus and computer program, in which: traffic is routed between a wide area network connection and a plurality of local network devices; the wide area network connection is formed in any of a plurality of connection types; each local network device of the plurality of the local network devices is identified; for each of the identified local network devices a suitable connection type is determined out of the plurality of connection types; and for each of the identified network devices the suitable connection type is arranged so that different ones of the identified network devices are able to communicate over the wide area network connection with different connection types.

Abstract: Provided is an operating method of a monitoring device configured to monitor a microcontroller unit including a plurality of cores. The operating method includes: transmitting a question message to a first core among the plurality of cores; receiving an answer message from a second core among the plurality of cores; determining whether an operation of the microcontroller unit is abnormal, by using the answer message; receiving answer messages from cores, except for the second core, among the plurality of cores when the operation of the microcontroller unit is abnormal; and detecting an error of each of the plurality of cores by using the received answer messages.

Abstract: The disclosure relates to a watchdog for monitoring a processor. The watchdog sends messages to the processor which subsequently sends back its own status information and optionally the status information of system components and the test results thereof at predetermined times as answers to the watchdog. The watchdog comprises at least one result memory in the form of, e.g., a shift register in which the watchdog records the history of the answers and examines patterns in erroneous answers. The recording is generated by a trigger event which can be the reception of individual answers and/or the end of scheduled reception time periods. According to the patterns, signalizations are carried out on the processor and/or other system components, which optionally introduce measures and adapt their structure and/or the implemented programs and/or the priority of said implementations.

Abstract: Example implementations described herein are directed to systems and methods for using and updating performance thresholds based on application characteristics. Example implementations compare monitored performance metrics with thresholds having similar application characteristics as the one monitored. Example implementations further manage remediation plans to solve performance issues based on application characteristics. In example implementations, management software retrieves existing plans created for similar situations in response to an issued alert.

Abstract: A method of dynamically allocating event data from a plurality of client devices among a set of event processors includes: at a partitioning controller, storing an initial shard map allocating initial subsets of the client devices to respective data stores, each data store associated with a respective one of the event processors; at the partitioning controller, obtaining an operational parameter for each of the event processors; at the partitioning controller, generating an updated shard map based on the operational parameter for each of the event processors, the updated map allocating updated subsets of the client devices to the respective data stores; responsive to generating the updated shard map, transmitting a map update notification from the partitioning controller for the client devices.

Abstract: Methods, systems and computer program products to measure system re-taskability are disclosed. The methods, systems and computer program products may be used in the design of a new or redesign of an existing System of Systems (SoS). Systems re-tasking (aka substitutability or stand-in redundancy) is the process of using different systems to substitute for non-operational systems to meet required functionality, or using multi-function systems to fulfill higher-priority tasks. This ability can increase the overall operational availability of the SoS; it can also increase the adaptability and resilience of the SoS to unknown or changing conditions. The disclosed methods, systems and computer products include simulating an SoS over time, replacing systems that become non-operational (or damaged) with systems that can fulfill the same capability in order to maximize the SoS availability.

Abstract: A computing device includes an interface configured to interface and communicate with a dispersed storage network (DSN), a memory that stores operational instructions, and a processing module operably coupled to the interface and memory such that the processing module, when operable within the computing device based on the operational instructions, is configured to perform various operations. The computing device is configured to receive write fanout request and process the write fanout request to determine parameters specified therein regarding a write fanout operation to be performed by the SU. The computing device then is configured to generate a plurality of replicated encoded data slices (EDSs) based on a plurality of EDSs in accordance with the parameters specified within the write fanout request to be stored within the DSN.

Abstract: Embodiments presented herein provide techniques for managing data in manufacturing systems. One embodiment includes receiving a set of data from a plurality of devices operating in a manufacturing environment. A portion of the set of data is written by a data management application to both a relational database and a distributed storage cluster that includes a plurality of storage nodes in a distributed computing environment. Upon receiving a query to extract a subset of data from the set of data, the query is analyzed to determine attributes of the query. Based, in part on the analysis, one of the relational database and the distributed storage cluster is selected for processing the query.

Abstract: Embodiments for selecting log snapshots for export in an automated data storage library by a processor. One or more log snapshots of an automated data storage library of an event displayed on a user interface of a device may be selected for exporting according to user defined criteria such that the one or more snapshots relate to the event or trigger, wherein the user interface provides an events table for searching and locating the event.

Abstract: Systems, methods, and computer-readable media are disclosed for validating endpoint information for nodes in a network. A network assurance appliance is configured to retrieve, from a first leaf node in a network, first endpoint information for a first set of endpoints connected to the first leaf node, wherein the first set of endpoints includes a virtual port channel (VPC) endpoint. The network assurance appliance retrieves second endpoint information from a second node in the network, compares the first endpoint information with the second endpoint information, and identifies an inconsistency when the first endpoint information and the second endpoint information do not match.

Abstract: In accordance with implementations of the present disclosure, a backup of live data received by a data forwarder is generated at the data forwarder while the live data is provided to a real-time data pipeline for forwarding from the data forwarder. A first portion of the live data is recovered from the backup to a stale data pipeline of the data forwarder. A request to forward the live data to a destination node is received by the data forwarder. In response to the request data is forwarded to the destination node, where the first portion of the live data from the stale data pipeline is added to a second portion of the live data from the real-time data pipeline in the response based on determining headroom remains to reach an amount of the data identified to include in the response.

Abstract: Methods and systems for a networked storage system are provided. One method includes filtering performance data associated with a resource used in a networked storage environment for reading and writing data at a storage device; and determining available performance capacity of the resource using the filtered performance data. The available performance capacity is based on optimum utilization of the resource and actual utilization of the resource, where utilization of the resource is an indicator of an extent the resource is being used at any given time, the optimum utilization is an indicator of resource utilization beyond which throughput gains for a workload is smaller than increase in latency and latency is an indicator of delay at the resource in processing the workload.

Abstract: Method and apparatus for a system to detect, address, and resolve defects, disfunctions, and inefficiencies in a distributed data environment. One or more diagnostics monitor specific operating parameters of specific services operating within the distributed data environment. When the diagnostic detects a service operating outside of a pre-determined threshold, an alert message is issued. Appropriate responses to the alert message assures that the system will maintain high availability protocol and will operate efficiently.

Abstract: A computer-implemented method for system performance verification is provided. The computer-implemented method includes invoking an integrated system tool to perform system performance verification of a client system. The computer-implemented method further includes monitoring administrative actions within an interface of the client system of an administrative device during the system performance verification. The computer-implemented method further includes recording screenshots of the monitored administrative actions, wherein the recorded screenshots are recorded to administrative log files of the administrative device. The computer-implemented method further includes transmitting the recorded screenshots to a storage location of system log files, wherein the recorded screenshots are associated with appropriate system log files for performing diagnosis of system performance verification of the client system.

Abstract: In some embodiments, a data set is selected based on one or more applications experiencing events. A first analysis of the data set is received that classifies the data set into a first set of failures using an analysis engine configured with first classification logic that performs the classifying. A portion of the data set is selected to re-run based on the first set of failures. A second analysis of the portion of the data set is received that classifies the portion of the data set into a second set of failures using the analysis engine that is configured with second classification logic. A correlation of one or more first failures that shift to one or more second failures is determined. An annotation describing the shift in the one or more first failures to the one or more second failures is then output.

Abstract: A livestock registration system according to an embodiment of the present technology includes an image data acquisition unit, a signal acquisition unit, and a registration unit. The image data acquisition unit acquires image data obtained by capturing an image of a target livestock animal. The signal acquisition unit acquires an individual identification signal transmitted from a transmission apparatus attached to the target livestock animal, the individual identification signal including an identifier for identifying the target livestock animal. The registration unit registers the identifier of the individual identification signal and the image data in association with each other, the identifier of the individual identification signal being received at a reception timing corresponding to a timing at which the image of the target livestock animal is captured.

Abstract: Extracting transaction level information from an interface can include tracking transactions of an interface within an integrated circuit (IC) using a plurality of counters within the IC, wherein the counters generate counter data corresponding to the transactions. The method can include capturing signals of the interface as trace data for a trace window using an integrated logic analyzer within the IC, wherein a start of the trace window begins after a start of the tracking of the transactions using the plurality of counters. The method can also include using a host data processing system coupled to the IC, determining transaction level information for the interface using the counter data and the trace data for the trace window.

Abstract: The invention relates to a fault-tolerant, maintainable automation system comprising two central computers, a process periphery and gateway computers, wherein the central computers and the gateway computers are fail-silent FCUs and represent autonomous exchange units, and the central computers and gateway computers exchange timed status messages via communications channels, and wherein each gateway computer establishes the link to the process periphery associated with the gateway computer and saves the current status of the process periphery associated with the gateway computer, and wherein a central computer assumes the role of an active central computer and another central computer assumes the role of a passive central computer, and wherein the active central computer exerts control over the gateway computers, and wherein the active central computer transmits a sign-of-life message to the passive central computer, preferably periodically, and wherein the passive central computer acknowledges the receipt of

Abstract: An apparatus comprises a memory and processing circuitry that are configured to implement a first network control protocol (NCP) MAC layer configured to handle MAC layer communications of the first NCP, and sniffer edge circuitry. The sniffer edge circuitry is configured to communicate with the first NCP MAC layer and a second NCP MAC layer and to capture events related to second NCP (WiGig) communications. These captured events are communicated over a dedicated sniffer network, and packet contents communicated between the second NCP MAC layer and the second NCP stack are secure from the sniffer edge circuitry. The apparatus receives a distributed common time reference and uses this to timestamp the captured events.

Abstract: The current application is directed to architected hardware support within computer processors for detecting and monitoring various types of potential performance imbalances with respect to simultaneously executing hardware threads in simultaneous multi-threading (“SMT”) processors and SMT-processor cores. The architected hardware support may include various types of performance-imbalance-monitoring registers that accumulate indications of performance imbalances and that can be used, by performance-monitoring software and by human analysts to detect performance-degrading conflicts between simultaneously executing hardware threads. Such conflicts can be ameliorated by changing the scheduling of virtual machines, tasks, and other computational entities, by redesigning and re-implementing all or portions of performance-limited and performance-degrading applications, by altering resource-allocation strategies, and by other means.

Abstract: A device may communicate with a server to obtain historical ticket data. The device may generate a data model, based on the historical ticket data. The device may communicate with a client device to obtain ticket data relating to an issue associated with a project. The device may classify, using the data model, the ticket data into a ticket type. The device may generate, using the data model and based on the ticket type, a set of recommended resolutions for resolving the issue associated with the project. The device may select, from the set of recommended resolutions, a particular resolution based on a set of selection criteria. The device may automatically perform one or more actions to implement the particular resolution to resolve the issue associated with the project.

Abstract: In one aspect, a system for providing automated root cause analysis of a monitored business transaction is disclosed. The system includes a processor; a memory; and one or more modules stored in the memory and executable by a processor to perform various operations. For example, a performance issue associated with the business transaction running in a monitored environment can be detected and automated root cause analysis can be provided to present to a user a chain of entities associated with detected performance issue. A score can be provided for each node of entity in the chain to indicate which node of entity is likelihood to be a root cause candidate for the performance issue.

Abstract: Techniques are disclosed for determining whether a computing node or a virtual machine instance executing on that computing node that is part of a web services platform is in an impaired condition or a normal condition. In embodiments, a status monitor of the web services platform obtains information about the status of the computing node or instance from multiple sources, aggregates this information to determine a cause of impairment and notifies a corresponding customer of this cause. In embodiments, the status monitor may also determine a possible remedy to this impairment and implement this remedy without customer input.

Abstract: The invention relates to a time-controlled distribution unit (30, 31) for the distribution of messages in a distributed computer system for safety-critical applications. Said distribution unit is designed as a self-testing functional unit and comprises input channels (201 . . . 222) for receiving time-controlled periodic input messages from node computers (20, 21, 22) upstream in the data flow, and output channels (301 . . . 333) for transmitting time-controlled periodic output messages to the node computers (50, 51, 52) downstream in the data flow, a computer (40) being provided in the distribution unit and being designed to analyze, by means of a “simple” software, useful information contained in the input messages, and to decide whether output messages are output and, if so, which useful information is contained in the output messages.

Abstract: A method of ensuring a correct program sequence in a dual-Processor module that includes Processor A and Processor B. Processor A and Processor B are both coupled to a common memory. Processor A and Processor B each execute a first safety program and each generate an instruction stream therefrom. At one or more points in time while running the first safety program, Processor A reads its program counter value from a current instruction being executed and generates therefrom a current Processor A CRC value, and Processor B reading its program counter value from the same current instruction being executed generates therefrom a current Processor B CRC value. Processor A transfers its current CRC value to Processor B and/or Processor B transfers its current CRC value to Processor A, and these CRC values are compared. A safety action is triggered if the comparing determines non-matching current CRC values.

Abstract: A method for a dispersed storage network (DSN) begins by receiving a read data object request from for a data object stored as a plurality of sets of encoded data slices in a set of storage units. The method continues by selecting a read threshold number of encoded data slices for retrieval. The method continues by issuing read slice requests to at least some of the storage units of the storage set to recover the selected read threshold number of encoded data slices. The method continues by receiving read slice responses from at least some of the storage units and selecting a decode threshold number of encoded data slices. The method continues by decoding the selected decode threshold number of encoded data slices to reproduce the data and generating audit information based on the selected slices for retrieval, the received slice, and the selected slices for decoding.

Abstract: There are disclosed computer-implemented methods, apparatus, and computer program products for scheduling snapshots. In one embodiment, the method comprises the following steps. The method comprises receiving performance data relating to a data storage system. The method also comprises determining, based on the performance data, a time for performing a snapshot of data stored on the data storage system. The method further comprises scheduling the snapshot according to the time.

Abstract: An apparatus for optimizing network traffic which includes a host computer having virtual machines (VMs); a monitoring module to collect network traffic data from the VMs; an analysis engine to receive the network traffic data from the monitoring module and to calculate metric values pertaining to the network traffic data; a pattern module to store network traffic patterns having metric values and to provide the network traffic patterns to the analysis engine, the analysis engine compares the calculated metric values to the network traffic pattern metric values and provides an output of a result of the compare of the calculated metric values to the network pattern metric values; and responsive to receipt of the output from the analysis engine, an optimization module processes the output and provides an optimization action to the VMs to improve the flow of the network traffic between the VMs.

Abstract: A method and system for conducting performance hybrid traffic testing of a networked target system (NTS) are disclosed. The method comprises initializing at least one private cloud source (PRCS) to generate traffic within a private network security system (PRNSS); initializing at least one public cloud source (PUCS) to generate traffic outside of the PRNSS; customizing the traffic within the PRNSS and the traffic outside of the PRNSS; gathering information respective of the performance of the at least one PUCS and the at least one PRCS; and generating a performance testing report respective of the gathered information.

Abstract: Technologies for managing replica caching in a distributed storage system include a storage manager device. The storage manager device is configured to receive a data write request to store replicas of data. Additionally, the storage manager device is configured to designate one of the replicas as a primary replica, select a first storage node to store the primary replica of the data in a cache storage and at least a second storage node to store a non-primary replica of the data in a non-cache storage. The storage manager device is further configured to include a hint in a first replication request to the first storage node that the data is to be stored in the cache storage of the first storage node as the primary replica. Further, the storage manager device is configured to transmit replication requests to the respective storage nodes. Other embodiments are described and claimed.