Abstract: Disclosed is a cloud computing system that includes: a core cloud part that stores and manages the cloud service in the core cloud server; and an edge cloud part that is arranged on a network node connected with the client terminal to form an edge cloud server, operates a portion or an entirety of a cloud service of the core cloud part at the edge cloud server, and stores and manages data of said service or receive cloud service packet information from the core cloud part to provide the cloud service to the client terminal. The edge cloud part includes an edge cloud awareness part that determines whether or not identification is possible for a cloud service request signal transmitted from a publisher client terminal, and an edge cloud processing part that determines whether or not to provide the cloud service corresponding to the request signal.

Abstract: Duration information indicative of an amount of time taken by each of one or more tasks of a distributed compute phase of a distributed compute job in a distributed compute cluster to execute is obtained. The one or more tasks are sorted into one or more groups based on the duration information and a resource requirement is determined for each of the one or more groups. A time-varying allocation of resources of the distributed compute cluster for the phase is determined based on the resource requirement for each of the one or more groups.

Abstract: A task allocating method for a reconfigurable processing system is provided by the present disclosure. The method includes determining a use status of a hardware processing resource of the reconfigurable processing system. The hardware processing resource includes m task channels and a reconfigurable computing array, and one task channel controls at least one operator in the reconfigurable computing array at a time to process one task. The number m is a positive integer and allocating a first task in n tasks to be processed according to the use status of the hardware processing resource, so that at least one task channel in the m task channels controls the reconfigurable computing array to process simultaneously at least one task which includes the first task, where the number n is a positive integer. A task allocating system for a reconfigurable processing system is also provided by the present disclosure.

Abstract: An example method to provide a storage service in a virtualized computing environment may include obtaining network latency information associated with various hosts in the virtualized computing environment. In response to identifying a first network latency value that exceeds a threshold, wherein the first network latency is between the first host and a second host in the virtualized computing environment, the method includes placing the second host in a first cohesive cluster consisting of the second host. In response to identifying a second network latency value being less than or equal to the threshold, wherein the second network latency value is between the first host and a third host in the virtualized computing environment, the method includes grouping the first host and the third host in a second cohesive cluster. The method includes initiating configuration of resources in the first cohesive cluster and the second cohesive cluster to support the storage service.

Abstract: A host system reallocates resources in a virtual computing environment by first receiving a request to reallocate a first quantity of a first resource type. Next, potential trade-off groups are evaluated and a trade-off group is selected based on the evaluation. The selected trade-off group includes a set of applications running in the virtual computing environment that can use one or more alternate resource types as a substitute for the first quantity of the first resource type. After the selection, the host system reallocates the first quantity of the first resource type from the trade-off group. This reallocation may be made from the trade-off group to either a first application running in the virtual computing environment or the host system itself. If the reallocation is to the host system, then the total quantity of the first resource type allocated to applications running in the virtual computing environment is thereby reduced.

Abstract: A resource scheduling device, system, and method are provided. The device includes: a data link interaction module and a dynamic resource control module. The data link interaction module is connected to an external server, at least two external processors, and the dynamic resource control module. The dynamic resource control module is connected to the external server, and is configured to monitor a task amount of a to-be-allocated task carried by the external server, generate, based on the task amount, a route switching instruction, and transmit the instruction to the data link interaction module. The data link interaction module is configured to receive the to-be-allocated task allocated by the external server and the route switching instruction transmitted by the dynamic resource control module and transmit, in response to the instruction, the to-be-allocated task to at least one target processor.

Abstract: The present disclosure provides methods, systems, and media for allowing access to quantum ready and/or quantum enabled computers in a distributed computing environment (e.g., the cloud). Such methods and systems may provide optimization and computational services on the cloud. Methods and systems of the present disclosure may enable quantum computing to be relatively and readily scaled across various types of quantum computers and users at various locations, in some cases without the need for users to have a deep understanding of the resources, implementation or the knowledge that may be required for solving optimization problems using a quantum computer. Systems provided herein may include user interfaces that enable users to perform data analysis in a distributed computing environment while taking advantage of quantum technology in the backend.

Abstract: Techniques for incremental workflow execution are provided. In one technique, a computing job in a workflow identifies an input path that indicates a first location from which the computing job is to read input data. The computing job identifies an output path that indicates a second location to which the computing job is to write output data. The computing job performs a comparison between the input path and the output path. Based on the comparison, the computing job determines whether to read the input data from the first location. If the input path does not correspond to the output path, then the computing job reads the input data from the first location, generates particular output data based on the input data, and writes the particular output data to the second location. The computing job ceases to execute if the input path corresponds to the output path.

Abstract: Implementations of the present disclosure include methods, systems, and computer-readable storage mediums for training ML models in aPaaS architectures including actions of receiving, at a training master provided using a first VM, a training request to train a ML model, the training request being received from a first tenant in a multi-tenant, aPaaS architecture, initiating, by the training master, training of the ML model by a training worker provided using a second VM, during training of the ML model, periodically updating training storage metadata based on metadata describing progress of the training of the ML model, and in response to completion of the training of the ML model, storing a trained ML model in a model storage of the aPaaS architecture.

Abstract: In an embodiment, a processor includes a plurality of cores and synchronization logic. The synchronization logic includes circuitry to: receive a first memory request and a second memory request; determine whether the second memory request is in contention with the first memory request; and in response to a determination that the second memory request is in contention with the first memory request, process the second memory request using a non-blocking cache coherence protocol. Other embodiments are described and claimed.

Abstract: Systems and methods are directed to efficient management of processor resources, particularly General Purpose Registers (GPRs), for example to minimize pipeline flushes prevent deadlocks by counting GPRs instead of allocating them to specific blocks of code. Blocks of code are allowed to execute if the Free GPRs count is adequate. The method contemplates counting the number of Register Writers in blocks of code which will write to GPRs which are in process of executing, and counting the GPRs which are available instead of merely allocating them to dedicated use by a block of code, or an instruction in a block of code. Because blocks do not run if there is not enough GPRs available for the block, deadlocks and pipeline flushes due to lack of resources can be minimized.

Abstract: A consumer transmits a set of system updates corresponding to an initial set of events retrieved from an event stream. The consumer determines that acknowledgement of the transmission of the initial set of events has not been received. The consumer executes another retrieval operation to retrieve events from the event stream which results in retrieving an updated set of events. The updated set of events includes the initial set of events and one or more additional events. The consumer trims the updated set of events to remove the one or more additional events and obtains the initial set of events. The consumer re-determines and re-transmits the system updates corresponding to the initial set of events that were obtained by trimming the updated set of events.

Abstract: Programmable devices, hierarchical parallel machines and methods for providing state information are described. In one such programmable device, programmable elements are provided. The programmable elements are configured to implement one or more finite state machines. The programmable elements are configured to receive an N-digit input and provide a M-digit output as a function of the N-digit input. The M-digit output includes state information from less than all of the programmable elements. Other programmable devices, hierarchical parallel machines and methods are also disclosed.

Abstract: A hyperconverged system is provided which includes an operating system; a core layer equipped with hardware which starts and updates the operating system and which provides security features to the operating system; a services layer which provides services utilized by the operating system and which interfaces with the core layer by way of at least one application program interface; and a user interface layer which interfaces with the core layer by way of at least one application program interface; wherein said core layer includes a system level, and wherein said system level comprises an operating system kernel.

Abstract: According to an embodiment, a notification control device includes a memory and one or more hardware processors configured to function as a determination unit and a notification unit. The determination unit is configured to determine, using notification control information set according to a priority of a frame, whether to notify of completion notification indicating completion of processing of the frame. The notification unit is configured to notify the completion notification when it is determined to notify of the completion notification.

Abstract: An operating system provides an extensible share action to broker content sharing between applications executing on a computing platform such as a personal computer, tablet computer, or smartphone. The share action enables a consistent user experience for content sharing to be implemented across all applications and eliminates users having to switch from the current application they are using to some other functionality in order to share content. Applications can participate with the operating system share action as source applications and/or target applications. Source applications may describe what content is shareable given the current state of their application when the user chooses to invoke the share action. Target applications can be configured to receive the shared content from the source application according to content type, and will expose a companion view of their application to the user that is specifically tailored to facilitate sharing.

Abstract: Methods and systems correlating hypotheses outcomes using relevance scoring for intuition based forewarning are disclosed. For one example, an intuition based forewarning method includes collecting and storing core data and surroundings data, wherein the core data includes parameters describing a system and ring data includes parameters describing surroundings of the system. The collected core data and ring data are analyzed to determine one or more changing situations of the system. A relevance score is provided for each determined changing situation of the system based on the analyzed core data and ring data. Each determined situation is correlated with one or more hypotheses outcomes representing a future system state based on the relevance score. A system forewarning is generated based on the correlated hypotheses outcomes which can be observed by one or more users.

Abstract: A method includes receiving a data set. The data set includes a plurality of data subsets wherein each data subset is associated with one transaction in a fully or partially masked network. The method further includes processing each data subset according to a plurality of rules to generate a plurality of activation values and an output for the each data subset. The plurality of activation values and the output for the each data subset form an activation pattern for the each data subset. The method also includes generating a predictive model based on the activation patterns. The method further includes identifying a subset of transactions as outliers based on the predictive model.

Abstract: A failure prediction system includes: one or more apparatuses; and a server that cooperates with the apparatuses to predict occurrence of a predetermined failure in a certain apparatus among the apparatuses, the server including a hardware processor that: collects data for predicting the occurrence of the failure, from the apparatuses; analyzes the collected data and obtains an important-feature amount for making a predetermined standard prediction model adapt to the certain apparatus; and transmits the obtained important-feature amount to the certain apparatus, and the certain apparatus including a hardware processor that: transmits the data of the certain apparatus to the server; receives the important-feature amount from the server; adjusts the standard prediction model with the received important-feature amount; and predicts the occurrence of the failure with application of the data of the certain apparatus to the adjusted prediction model.

Abstract: A method is provided for healing reset errors for a magnetic memory using destructive read with selective write-back, including for example, a self-referenced read of spin-torque bits in an MRAM. Memory cells are prepared for write back by one of identifying memory cells determined in error using an error correcting code and inverting the inversion bit for those memory cells determined in error identifying memory cells determined in error using an error correcting code and resetting a portion of the memory cells to the first state; and resetting one or more memory cells to the first state.

Abstract: Systems and methods for managing and repairing errors occurring on a plurality of servers in an automated server build process is provided. Systems may include a first error code from a plurality of error codes. The first error code may be associated with a failure. The system may further include a plurality of sets of action codes. When the failure occurs on a server, included in the plurality of servers, during the server build process, the system may be configured to receive an error code from the server that may correspond to the failure and check the error code against previously recorded error codes recorded on an error code table. When the error code is included in the error code table, the system may retrieve the corresponding action code, assign the action code to the failure and execute the action code on the server.

Abstract: Managing real-time monitoring alerts is provided. An alert is generated for one or more metrics exceeding corresponding defined metric threshold values. A root cause dependency table showing relationships between alerts is retrieved. It is determined whether current real-time metrics are needed from one or more monitoring agents that correspond to dependent alerts not triggered in an alert chain of the generated alert based on information in the root cause dependency table. In response to determining that the current real-time metrics are needed from the one or more monitoring agents that correspond to the dependent alerts not triggered in the alert chain of the generated alert based on the information in the root cause dependency table, the current real-time metrics are requested from the one or more monitoring agents that correspond to the dependent alerts not triggered in the alert chain.

Abstract: Managing real-time monitoring alerts is provided. An alert is generated for one or more metrics exceeding corresponding defined metric threshold values. A root cause dependency table showing relationships between alerts is retrieved. It is determined whether current real-time metrics are needed from one or more monitoring agents that correspond to dependent alerts not triggered in an alert chain of the generated alert based on information in the root cause dependency table. In response to determining that the current real-time metrics are needed from the one or more monitoring agents that correspond to the dependent alerts not triggered in the alert chain of the generated alert based on the information in the root cause dependency table, the current real-time metrics are requested from the one or more monitoring agents that correspond to the dependent alerts not triggered in the alert chain.

Abstract: A system LSI including: a first group including a first CPU and a first module; a second group including a second CPU and a second module having the same configuration as the first module has; and a shared memory including a first area for which cache coherency is maintained by an access from the first group, and a second area for which cache coherency is maintained by an access from the second group, the shared memory electrically connected to the first group and the second group. The first group includes a first bus through which cache coherency is maintained between the first CPU and the first module, and a second bus which electrically connects the first bus and the first module to each other. The second group includes a third bus through which cache coherency is maintained between the second CPU and the second module, and a fourth bus which electrically connects the third bus and the second module to each other.

Abstract: A method and system for performing a root cause analysis. A CPU identifies events of interest as a function of a user's observable behavior, which includes the user's eye gaze, while viewing event data. The CPU calculates an interest score for each of the identified events of interest, wherein the interest score is a probability of each of the identified events of interest being a root cause of a defect. The CPU tags each of the events of interest with a tag as a function of each calculated interest score. The identifying of the one or more events of interest includes: correlating a focal point of the user's eye gaze to a viewing position of a display device displaying the file; and identifying, as a function of the viewing position, the event data being viewed and an amount of time that the event data is viewed by the user.

Abstract: Disclosed herein are systems, devices, and methods related to assets and asset operating conditions. In particular, examples involve defining and using a predictive model that is configured to output an indication of whether at least one failure type from the group of possible failure types is likely to occur at an asset within the given period of time in the future.

Abstract: Methods and systems for detecting anomalous behavior include performing a principal component analysis on a plurality of key performance indicators (KPIs) to determine a set of principal axes. The KPIs are clustered in a space defined by the set of principal axes. Local anomalies are determined in the clustered KPIs by comparing, for each individual KPI in clusters that conform to a Gaussian distribution, a distance from a respective cluster mean to a threshold. Structural anomalies are determined in the clustered KPIs. The structural and local anomalies are classified based on historical information. A management action is performed based on the classified structural and local anomalies.

Abstract: Methods and systems for detecting anomalous behavior include performing a principal component analysis on a plurality of key performance indicators (KPIs) to determine a set of principal axes. The KPIs are clustered in a space defined by the set of principal axes. Local and structural anomalies are determined in the clustered KPIs. The structural and local anomalies are classified based on historical information. A transformation is performed from a space based on the principal axes to an original space. It is determined whether each of the local and structural anomalies is a global or a local anomaly. A management action is performed based on the classified structural and local anomalies.

Abstract: A method and associated systems use DVFS performance-scaling technology to satisfy quality-of-service performance requirements when recovering a job that had been scheduled to run on a failed virtual machine. A Buffer Time specifies a duration of time remaining, at the time of failure, for the job to complete in order to satisfy the quality-of-service requirements. Depending on relative durations of time required to repair the failed virtual machine, to perform the job on an unsealed active-mode virtual machine, and to transfer the job to another virtual machine, the system determines whether to repair the failed virtual machine or to transfer the job. If the latter, the system then determines whether to select a destination virtual machine provisioned on a DVFS-compliant platform and, if so, the system scales the DVFS-compliant platform's performance to a level sufficient to complete the job within the Buffer Time.

Abstract: An arithmetic processing device according to an embodiment performs actual arithmetic processing for data inputted periodically and determination whether or not an error occurs in the actual arithmetic processing in real time. An ISP of this device includes an arithmetic processing circuit for performing image arithmetic processing for image data in moving image inputted from imaging device at each of frames, and a diagnostics control circuit and diagnostics processing circuit connected to the arithmetic processing circuit. The ISP, with these components, performs the image arithmetic processing for the image data in the moving image at each of the frames and error detection in the image arithmetic processing in real time.

Abstract: An error detection circuit, applied to a digital communication system with embedded clock, includes a time delay unit, a clock embedding encoding unit, a comparing unit and a packet error counting unit. The time delay unit delays a first digital encoded signal for a period of time. The clock embedding encoding unit generates a second digital encoded signal according to a first digital decoded signal, wherein the first digital decoded signal is generated by decoding the first digital encoded signal. The comparing unit is coupled to the time delay unit and the clock embedding encoding unit respectively and compares the first digital encoded signal with the second digital encoded signal to generate a compared result. The packet error counting unit is coupled to the comparing unit and counts a packet error rate according to the compared result and then provides a flag according to the packet error rate.

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 processing circuitry operably coupled to the interface and to the memory. The processing circuitry is configured to execute the operational instructions to perform various operations and functions. The computing device obtains directory metrics associated with a directory structure that is associated with a directory file that is segmented into a plurality of data segments and based on a determination to reconfigure the directory structure based on the directory metrics, the computing device determines a number of layers for a reconfigured directory structure, a number of spans per layer of the number of layers for the reconfigured directory structure, and directory entry reassignments. The computing device reconfigures the directory structure based on the number of layers, the spans per layer, and the directory entry reassignments.

Abstract: A memory device is configured to perform a parallel read-modify-write operation, which generates a syndrome for first partial data read from a memory cell array and second partial data according to a data mask option, corrects an error of the second partial data, generates merged data by combining second data with the corrected second partial data, and generates an internal parity for the merged data. The memory device sets the second partial data to binary values of 0, generates third data by combining the second partial data set to the binary values of 0 with the second data, generates a third parity for the third data, and generates an internal parity for the merged data based on the syndrome, a partial parity, and the third parity.

Abstract: In general, according to an embodiment, a memory system includes a memory device including a memory cell; and a controller. The controller is configured to: receive first data from the memory cell in a first data reading; receive second data from the memory cell in a second data reading that is different from the first data reading; convert a first value that is based on the first data and the second data, to a second value in accordance with a first relationship; and convert the first value to a third value in accordance with a second relationship that is different from the first relationship.

Abstract: According to an embodiment, a memory system includes: a test pattern decoding unit that detects an intermediate decoding word from a plurality of test patterns; a Euclid distance calculating unit that calculates a Euclid distance between the intermediate decoding word and a received word; and a maximum likelihood decoding word selecting unit that maintains a maximum likelihood decoding word candidate. In a case where a Euclid distance of the intermediate decoding word is shorter than a Euclid distance of the maximum likelihood decoding word candidate, the maximum likelihood decoding word selecting unit updates the maximum likelihood decoding word candidate by using the intermediate decoding word and the test pattern decoding unit does not execute decoding of a test pattern having no possibility that the Euclid distance of the intermediate decoding word becomes shorter than the Euclid distance of the maximum likelihood decoding word candidate.

Abstract: According to one embodiment, a memory system includes a nonvolatile memory, an encoding part configured to generate a plurality of component codes including a first component code and a second component code different from the first component code, by using, as an information symbol, at least one symbol of a plurality of symbols included in user data to be written into the nonvolatile memory, and a memory interface configured to write the plurality of component codes into the nonvolatile memory. The encoding part includes a plurality of encoders each configured to generate a parity corresponding to each of the plurality of component codes, and a first distributor configured to divide a first symbol string of the user data into a plurality of chunks, each of which has a first symbol length smaller than that of the first symbol string, and to input each of the plurality of chunks generated by the division, into any one f at least different two of the plurality of encoders.

Abstract: Some embodiments include apparatuses and methods using a first memory area and a second memory area included a memory device, and using control circuitry included in the memory device to communicate with a memory controller. The memory controller includes an error correction engine. The control circuitry of the memory device is configured to retrieve the first information from the first memory area and store in the first information after the error correction engine performs an error detection operation on the first information. The control circuitry is configured to retrieve second information from the first memory area and store the second information in the second memory area without an additional error detection operation performed on the second information if a result from the error detection operation performed by the error correction engine on the first information meets a threshold condition.

Abstract: The invention relates to a storage system comprising one or more storage controllers, two or more storage devices and two or more storage clients, the storage controllers, the storage devices and the storage clients being coupled via a network in order to exchange information between the storage controllers, said storage devices and said storage clients, wherein each storage client is adapted to provide data-path-storage commands to the storage devices via the network bypassing the storage controllers, wherein the storage system is adapted to provide data redundancy using a data redundancy scheme higher than RAID 1.

Abstract: A method begins by a processing module of a dispersed storage network (DSN) receiving content from a data source for storage in the DSN. The method continues with the processing module transforming the content into a plurality of formats of a set of set of formats according to a formatting scheme and dispersed storage error encoding each format of the plurality formats to produce a corresponding plurality of sets of encoded data slices. The method continues with the processing module generating a logical address for each format, and generating a corresponding plurality of sets of slice names for each logical address. The method continues with the processing unit facilitating storage of the corresponding set of encoded data slices in a set of storage units using the corresponding plurality of sets of slice names.

Abstract: Methods for use in a dispersed storage network (DSN) to retrieve encoded data from memory device of an impaired storage unit. In various embodiments, a computing device of the DSN issues requests to a plurality of storage units, including the impaired storage unit, to recover at least a decode threshold number of encoded data slices of a set of encoded data slices. When the impaired storage unit determines that it is not able to quickly retrieve the requested data slice for provision to the computing device, the impaired storage unit promptly issues a quasi-error response instead. In response to receiving less than the decode threshold number of encoded data slices and a quasi-error response, the computing device determines to issue another slice request(s) to another storage unit(s) and/or issue a continue request instructing the impaired storage unit to continue processing the request to recover the data slice stored therein.

Abstract: Data targeted for storage into a drive array is divided into codewords with data and parity symbols. The symbols of the codewords are randomly distributed across a stripe of the drive array. One or more drives affected by data corruption are found based on a probability that a subset of inconsistent codewords intersects the one or more drives.

Abstract: A data storage system can have multiple parity redundancy with a plurality of data storage units arranged into logical rows and logical columns. A controller connected to the plurality of data storage units can orchestrate the logical rows storing striped data having at least one rotational parity value and each logical column storing striped data with a static parity value. The static parity value of each logical column may be computed from the at least one rotational parity value of at least one logical row as directed by the controller.

Abstract: Examples disclosed herein relate to using a programmable logic device to perform a recovery operation on non-volatile storage devices. In response to receiving an indication to perform recovery, multiple storage devices are set to a predetermined value by the PLD. Recovery of the storage devices is to begin based on the predetermined value setting.

Abstract: The present disclosure generally relates to recovering storage devices in-field without the need to return the storage device to the factory. The storage device tracks detailed failure information. After receiving a signal or sequence of commands from a host device to prepare the storage device for a recovery download, the storage device determines whether to enter an adaptive field recovery state or a host-selected recovery state. If the storage device enters the adaptive field recovery state, the storage device determines which error state the device is in based on the detailed failure information, and selects an appropriate recovery level. After selecting the appropriate recovery level while in the adaptive field recovery state or after entering the host-selected recovery state, the storage device receives and downloads a recovery download package. The recovery download package comprises one or more recovery actions necessary to repair the error state.

Abstract: A memory system includes a volatile memory, a nonvolatile memory, and a controller. The controller is configured to execute a non-volatilization process to store data in the volatile memory into the nonvolatile memory in response to an initiate request received by the controller if no cancellation request is received by the controller during a cancelable period that begins upon receipt of the initiate request by the controller, and to transmit a completion notification when the non-volatilization process has completed.

Abstract: A method, article of manufacture, and apparatus for processing data. In some embodiments, this includes analyzing a first container at a block level, determining a first level of granularity based on the analysis of the first container, based on the first level of granularity, identifying a first set of data objects, storing metadata of the first set of data objects in a recovery catalog, based on the first set of data objects, identifying a second container, analyzing the second container at a block level, determining a second level of granularity based on the analysis of the second container, based on the second level of granularity, identifying a second set of data objects, storing metadata of the second set of data objects in the recovery catalog, wherein the recovery catalog is stored in a storage device.

Abstract: Techniques are described for exchanging files between users via a server environment that maintains copies of file system data from user computing devices. For example, the server environment can maintain a copy of file system data from the file system of a first computing device associated with a first user. The server environment can receive a file request from a second user that requests a file (e.g., by describing the file) from the first user whose files are backed up at the server environment. The server environment can send a request to the first user to approve the file request. After receiving approval, the server environment can send the file to the second user (e.g., as an automatic download to a computing device associated with the second user).

Abstract: Technologies are described herein for providing secure data protection and recovery. A virtual data center can be created on backup servers to manage data backup for a specific client. Backups can be performed by a master server in the virtual data center initiating a secure network connection with a client computing device at a random or pseudo random time within a backup window specified by the client. A backup agent on the client computing device can execute a data mover program complied at the client's computing system but received from the master server to retrieve and save backup data at a random or pseudo random temporary location. The saved data can be transmitted and stored on data storage accessible only by a storage server. Backup data can be inspected in an isolated inspection server and be made retrievable through a secure data repository accessible by the client.

Abstract: An improved content indexing (CI) system is disclosed herein. For example, the improved CI system may include a distributed architecture of client computing devices, media agents, a single backup and CI database, and a pool of servers. After a file backup occurs, the backup and CI database may include file metadata indices and other information associated with backed up files. Servers in the pool of servers may, in parallel, query the backup and CI database for a list of files assigned to the respective server that have not been content indexed. The servers may then request a media agent to restore the assigned files from secondary storage and provide the restored files to the servers. The servers may then content index the received restored files. Once the content indexing is complete, the servers can send the content index information to the backup and CI database for storage.

Abstract: An improved content indexing (CI) system is disclosed herein. For example, the improved CI system may include a distributed architecture of client computing devices, media agents, a single backup and CI database, and a pool of servers. After a file backup occurs, the backup and CI database may include file metadata indices and other information associated with backed up files. Servers in the pool of servers may, in parallel, query the backup and CI database for a list of files assigned to the respective server that have not been content indexed. The servers may then request a media agent to restore the assigned files from secondary storage and provide the restored files to the servers. The servers may then content index the received restored files. Once the content indexing is complete, the servers can send the content index information to the backup and CI database for storage.