Abstract: Disclosed herein are system, method, and computer program products for storing a snapshot of block-level changes in a data volume using a file system-level backup tool. An embodiment operates by receiving the block level changes in the snapshot from the data volume stored in an application in a cluster. The embodiment creates a root directory for the snapshot. The root directory may have one or more subdirectories. The embodiment maps one or more block changes in the data volume onto the one or more subdirectories and creates a manifest for identifying the snapshot in the file system-level backup tool. The manifest may be associated with the root directory. The embodiment then instructs the file system-level backup tool to store the snapshot by storing the root directory in content-addressable object storage based on the one or more subdirectories and storing the manifest in a manifest storage.

Abstract: A snapshot request for a selected database is obtained by a computing device of a computing environment. Based on obtaining the snapshot request, a snapshot of the selected database is taken. Based on taking the snapshot, a snapshot identifier is recorded in metadata of the selected database. The snapshot identifier identifies the snapshot request.

Abstract: A system can perform a migration. The system can, in response to receiving a request to perform a file system operation on a destination file system, wherein the request identifies a first source file handle, direct, by a second computer and to a first computer, to perform the file system operation on a source file system with the first source file handle, to produce a second source file handle, convert the first and second source file handles to corresponding first and second components of a destination file handle, perform the file system operation on the destination file system with the first and second components of a destination file handle, respond to the client computer with the second source file handle. The system can re-assign a network address when rolling back the migration, wherein a client is configured to use the second source file handle with the source file system.

Abstract: A data storage environment can include one or more virtual machines instantiated on a host computing device. Based on physical location data of the one or more virtual machines received from the host computing device, a storage manager can control the performance of a secondary copy operation on one or more storage units that store virtual machine data associated with the one or more virtual machines and/or the performance of a secondary copy operation on the one or more virtual machines.

Abstract: Transmission of data for object storage, such as stream transmission for object storage, is disclosed. For instance, a group of objects acquired from an object layer is stored in a storage space for storing an object stream and serves as a first part of the object stream; and, in response to that an event related to at least one object in the group of objects occurs at a client terminal, the event-related information is stored in the storage space and is used as a second part of the object stream, the event-related information including at least one of the following: an identifier of the at least one object, a type of the event, and metadata of the event.

Abstract: A system, method, and computer program product for treatment planning are disclosed. The system includes at least one processing component, at least one memory component, a training module, a retrieval module, and a plan generator. The training module generates hash codes by hashing features from data sources with data source-specific hash functions, and generates superclass hash codes by hashing the generated hash codes with at least one superclass hash function. The retrieval module extracts features from case data, and locates features from the data sources that are similar to the extracted features. The plan generator calculates outcome probabilities for the case data based on known outcomes associated with the located features.

Abstract: A method for managing computing resources includes obtaining, by a resource use manager, a physical asset request from a client, in response to the physical asset request: initiating allocation of a landing area device to the client based on the physical asset request, determining a physical asset to be provided to the client, sending, to a manufacturer, a physical asset preparation request, obtaining a confirmation of deployment of the physical asset from the client, performing a restoration on the physical asset using a most recent landing area incremental backup, and after the initiating the restoration, initiating a transfer of operation from the landing area device to the physical asset.

Abstract: Technology described herein can globally perform management of virtual inode numbers (VINs) of all snapshots of a real filesystem. In an embodiment, a system can comprise a processor and a memory that stores executable instructions that, when executed by the processor, facilitate performance of operations. The operations can comprise, in response to a request to generate a primary snapshot of a real filesystem, allocating a primary instance of an individual VIN for a virtual inode corresponding to the primary snapshot, resulting in an allocated VIN having associated therewith a weight expressed as a value. The operations further can comprise storing the weight for the allocated VIN at a corresponding VIN metadata object exclusive to the VIN.

Abstract: Techniques are provided for coordinating snapshot operations across multiple file systems. A notification may be received that a snapshot of data stored across a persistent memory file system and a storage file system is to be generated. Forwarding, of modify operations from a persistent memory tier to a file system tier for execution through the storage file system, may be enabled. Framing may be initiated to notify the storage file system of blocks within the persistent memory file system that comprise more up-to-date data than corresponding blocks within the storage file system. In response to the framing completing, a consistency point operation is performed to create the snapshot and to create a snapshot image as part of the snapshot.

Abstract: Data protection methods and systems for a storage environment are provided. A first-in-first out (FIFO) structure stores a logical representation of a first storage location that retains previous data for a data container, after new data for the data container is stored at a second storage location. The FIFO structure also stores a logical representation of a file system tree structure that is stored in persistent storage, after a consistent point operation. In response to an event, the file system tree structure is selected, based on the file system tree structure being closest to a transaction. A snapshot is generated using the file system tree structure. Thereafter, the data container is restored from the snapshot or from a copy of the snapshot.

Abstract: A method and system for capturing dynamic data from data fields of a product has been developed. The method includes first collecting a product data set with multiple data fields. Static data fields of the product data set are identified that contain pre-defined standardized data for multiple other data sets. Next, dynamic data fields of the data set are identified. A dynamic data field is created by a user and contains additional data that is unique and applicable only to the product data set. The static data fields and the dynamic data fields are stored separately in a database repository for later recovery.

Abstract: An apparatus to facilitate descriptor resiliency in a computer system platform is disclosed. The apparatus comprises a non-volatile memory to store firmware for a computer system platform, wherein the firmware comprises a primary descriptor including access permission details for platform components and a secondary descriptor including a backup copy of the access permission details and a controller, coupled to the first non-volatile memory, including recovery hardware to detect a problem during a platform reset with the primary descriptor, recover the contents of the primary descriptor from the backup copy included in the secondary descriptor and store the contents of the backup copy to primary descriptor.

Abstract: An information processing apparatus includes: a memory; and a processor coupled to the memory and configured to: perform mirroring of data with a first information processing apparatus and switches from a standby system to an active system with operation shutdown of the first information processing apparatus to operate as a second information processing apparatus, the information processing apparatus; determine whether or not target data is data for which the mirroring is completed before the operation shutdown, the target data being target data of a restoration copy processing performed when the first information processing apparatus is restored to the active system after the information processing apparatus operates as the second information processing apparatus; and copy the target data from the own apparatus to the first information processing apparatus when determining that the target data is data for which the mirroring is completed.

Abstract: A distributed data warehouse system maintains data blocks on behalf of clients, and stores primary and secondary copies of data blocks on different disks or nodes in a cluster. The data warehouse system may back up data blocks in a key-value backup storage system. In response to a query targeting a data block previously stored in the cluster, the data warehouse system may determine whether a consistent, uncorrupted copy of the data block is available in the cluster (e.g., by applying a consistency check). If not (e.g., if a disk or node failed), the data warehouse system may automatically initiate an operation to restore the data block from the backup storage system, using a unique identifier of the data block to access a backup copy. The target data may be returned in a query response prior to restoring primary and secondary copies of the data block in the cluster.

Abstract: A computer-implemented method according to one approach includes identifying an inability to access a first storage volume during a first data replication session, creating a second data replication session including the first storage volume, and removing the first storage volume from the first data replication session.

Abstract: Multiple substantially concurrent data streams with NDMP protocol improve robustness, performance, and granularity of backup and restore operations from/to a filer. NDMP data streams are initially allocated based on inventorying the root level of each filer volume. A best effort to balance the multiple NDMP data streams allocates them based on data amounts used in each volume. Orphaned files are also collected and backed up. Subsequent full backup jobs leverage a proprietary index generated in preceding full backup jobs to obtain better performance and to better balance the NDMP data streams by creating substantially co-equal groupings of source data. The index comprises granular information which is not available from querying the filer. The size of each individual backup copy from a preceding full backup job and/or the size of subtending subdirectories or individual backed up files therein is used by later backup jobs to fine tune NDMP data stream allocation.

Abstract: Embodiments allow a primary database system (“primary”) to automatically detect queries directed to the primary database that may be offloaded to a standby database system (“standby”), and then to automatically offload the offload-eligible queries to a standby. The primary identifies offload-eligible queries based on a record of up-to-date database objects within each standby that replicates the primary database. The record of up-to-date standby objects is updated based on heartbeat messages from each standby, and commit timestamps for transactions on the primary. Evaluation of whether a query is offload-eligible is triggered by one or more trigger conditions that include: inclusion of an offload optimizer hint in the query, an estimated run-time of the query, etc. Embodiments further allow an offloaded query over particular changed data in the primary database to access, on a standby database, uncommitted changes made to the particular data in the primary database.

Abstract: An object dataset creation or modification mechanism is provided for object dataset creation or modification using a labeled action-object video. For a plurality of frames of the labeled action-object video, an identification is made of a subset of frames where a bounding box object (BBO) exists. BBOs in the subset of frames where a BBO exists are pruned to identify sufficiently distinct BBOs thereby forming a set of pruned BBOs. For each pruned BBO in the set of pruned BBOs: an information addition score is determined; the information addition score is assessed; responsive to the information addition score being positively assessed, the pruned BBO is added to an object dataset; and, responsive to the information addition score being negatively assessed, the pruned BBO is discarded.

Abstract: A system and method for enabling data replication is described. A set of protocol messages can be associated with a set of corresponding set of requests. The associated set of protocol messages can be provided to each of a source storage system and a destination storage system. The source storage system and the destination storage system can be heterogeneous storage systems that implement different types of file systems or file layouts. The source storage system and the destination storage system are enabled to perform a data replication process, in which at least a set of data is to be replicated from the source storage system to the destination storage system, using at least a protocol message from the associated set of protocol messages. The protocol message can correspond to a request for a list of snapshots stored at the source storage system.

Abstract: Systems and methods are disclosed for processing and executing queries in a data intake and query system. An indexing system of the data intake and query system receives data from an ingestion buffer that includes a marker that indicates data that is made available to the indexing system. The data intake and query system stores at least a portion of the data in buckets and stores the buckets in a shared storage system. Based on the storage of the buckets in the shared storage system, the indexing system indicates to the ingestion buffer that the marker can be updated.

Abstract: According to embodiments of the present invention, a metadata file is transferred from the first system to the second system and a database on the second system is initialized based on the metadata file. An image, including information of the first system to be restored, is transferred from the first system to the second system, and restoration of the information to the second system based on the image is initiated. Prior to completion of the restoration, one or more log files indicating actions performed on the first system relating to the information to be restored is transferred from the first system to the initialized database on the second system. In response to completion of the restoration, the actions of the log files are performed to synchronize the restored data on the second system with the first system.

Abstract: According to embodiments of the present invention, a metadata file is transferred from the first system to the second system and a database on the second system is initialized based on the metadata file. An image, including information of the first system to be restored, is transferred from the first system to the second system, and restoration of the information to the second system based on the image is initiated. Prior to completion of the restoration, one or more log files indicating actions performed on the first system relating to the information to be restored is transferred from the first system to the initialized database on the second system. In response to completion of the restoration, the actions of the log files are performed to synchronize the restored data on the second system with the first system.

Abstract: A method for analyzing data corruption is disclosed. In one embodiment, such a method includes identifying a data set to analyze for data corruption. This data set resides on tracks of a volume. The method further determines, from control information associated with the volume, on which tracks of the volume the data set resides. The method reads content of the data set without opening the data set by performing full-track reads of the tracks. The method further determines an expected format of the content by analyzing the control information. An actual format of the content is compared to the expected format to identify areas of the data set that may be corrupt. A corresponding system and computer program product are also disclosed.

Abstract: A storage system includes a storage array having physical storage resources, a Software Defined Network Attached Storage (SDNAS) process running in an emulation on the storage system, a user file system having user file system data stored in the storage array that is accessed by the SDNAS process via a first Thin Logical Unit (TLU) storage volume mounted on an emulation operating system, a snapshot copy of the user file system stored in the storage array, and control logic. In some embodiments, the control logic is configured to associate a logical view of the snapshot copy of the user file system to a second TLU, mount the second TLU on the emulation operating system as a snapshot copy file system, and replay pending transactions and sub-transactions of the user file system on the snapshot copy file system to bring the snapshot copy file system to a stable state.

Abstract: Provided are an apparatus and a method for replicating changed-data in a source database management system to a target database management system in real time, for minimizing the load on the source DBMS system, reducing costs for DBMS hardware configuration, and facilitating operation and failure recovery. The source server transmits the changed-data from a redo log file or an archive log file in a source DBMS area to a target server in real time, and the target server receives the changed-data transmitted from the source server to temporarily store the changed-data in a local area, and extracts the change data stored in the local area to replicate the extracted changed-data to the target DBMS, thereby implementing the apparatus for replicating the changed-data in the source database management system to the target database management system in real time.

Abstract: A system and method are disclosed for managing snapshots of a distributed file system. In accordance with one implementation, a list of snapshots of a file system is presented to a user, where the snapshots include one or more active snapshots and one or more inactive snapshots. A request by the user to access one of the snapshots in the list is received. In response to determining that the requested snapshot is active, the user is provided access to the requested snapshot. In response to determining that the requested snapshot is inactive, the requested snapshot is activated and the user is provided access to the requested snapshot.

Abstract: An execution platform comprising a workflow engine and an application engine is provided. A workflow definition associated with an application is received. The workflow definition is used to run an application workflow to perform an action with respect to the application, at least in part by causing an executable binary to be run by the application engine.

Abstract: Disclosed are systems and methods of synchronization between a source and a target. The synchronization relationship can be quickly and easily be created for disaster recovery, real-time backup and failover, thereby ensuring that data on the source is fully-protected at an off-site location or on another server or VM, for example, at another data center, a different building or elsewhere in the cloud. Common snapshots available on both the source and target can act as common recovery points. The common recovery points can be used to locate the most recent snapshot in common, between the source and target, to enable a delta sync of all subsequently written data at the source to the target after an offline event.

Abstract: A system and method for enabling data replication is described. A set of protocol messages can be associated with a set of corresponding set of requests. The associated set of protocol messages can be provided to each of a source storage system and a destination storage system. The source storage system and the destination storage system can be heterogeneous storage systems that implement different types of file systems or file layouts. The source storage system and the destination storage system are enabled to perform a data replication process, in which at least a set of data is to be replicated from the source storage system to the destination storage system, using at least a protocol message from the associated set of protocol messages. The protocol message can correspond to a request for a list of snapshots stored at the source storage system.

Abstract: In a method for implementing data conversion in a cloud data center, a backup server receives a read request from a block storage server. The read request includes a uniform resource locator (URL) address of a to-be-read virtual image object on the backup server and an address range of target data in the to-be-read virtual image object. The backup server obtains an address mapping bitmap and a storage path of backup data in a backup replica corresponding to the to-be-read virtual image object according to the URL address. Thereafter, the backup server obtains the target data from a storage device according to the address range of the target data and the address mapping bitmap and the storage path. Further, the backup server sends the target data to the block storage server. Hence, the conversion time of a backup data object may be shortened.

Abstract: One or more techniques and/or computing devices are provided for secure data replication. For example, a first storage controller may host first storage within which storage resources (e.g., files, logical unit numbers (LUNs), volumes, etc.) are stored. The first storage controller may establish an access policy with a001 second storage controller to which data is to be replicated from the first storage. The access policy may define an authentication mechanism for the first storage controller to authenticate the second storage controller, an authorization mechanism specifying a type of access that the second storage controller has for a storage resource, and an access control mechanism specifying how the second storage controller's access to data of the storage resource is to be controlled. In this way, data replication requests may be authenticated and authorized so that data may be provided, according to the access control mechanism, in a secure manner.

Abstract: A method is used in managing file deletions in storage systems. A request to delete a set of replicas of a file of a file system is received. A replica of the file represents a state of the file at a particular prior point in time. A sibling indirect block associated with a portion of the file identified for deletion is identified. The sibling indirect block includes a set of file system blocks. A set of indirect blocks associated with replicas of the file is identified. The sibling indirect block and the set of indirect blocks share a subset of the set of file system blocks where the set of indirect blocks have been identified for deletion. Weight information associated with the subset of the set of file system blocks shared among the set of indirect blocks that have been pending deletion is merged. The set of indirect blocks are processed for deletion concurrently. Metadata of the sibling indirect block is updated with the merged weight information.

Abstract: Currently, administrators configure replication manually according to a data protection policy. Typically, such data protection policies are provided via a script or a similar input to provision storage devices. However, such manual configuration is subject to administrator error. For example, an administrator may not provision storage devices accurately according to a desired data protection policy. Further, this process is subject not only to human mistake, but also the administrative overhead required to manually provision the storage devices. Example embodiments of the present invention eliminate administration and reliability issues arising out of manual replication service configuration, thereby minimizing administrative costs and improving the user experience of handling data protection. Example embodiments of the present invention provide a method, an apparatus and a computer-program product for creating a policy-based replication service.

Abstract: An information processing device includes a control unit, a hash unit, and a comparison unit. The control unit runs a program and to store flow control information of the program in a call stack. The hash unit generates a first hash value by applying a hash function to selected data in response to a first context change of the program. The control unit starts or resumes a second process or thread of the program only when the hash unit has generated the first hash value. The hash unit generates a second hash value by re-applying the hash function to the selected data in response to a second context change. The first and second context changes include a termination or interruption of the first process or thread and the second process or thread. The comparison unit determines whether the first hash value and the second hash value are identical.

Abstract: A data protection technique maintains replicas of both a data object and its snaps by conducting replication operations on the data object between a source and a destination. The technique includes generating a pair of content-consistent snaps, one snap of the data object at the source and one snap of its replica at the destination. A common snap signature identifies both snaps of the pair of content-consistent snaps. Orchestration of replication ensures that both snaps of the pair share the same content. The two snaps may thus be used interchangeably, with the snap of the replica at the destination providing essentially a backup of the snap of the data object at the source.

Abstract: Techniques to back up data are disclosed. In various embodiments, a copy of a free block map as of a first time associated with a first backup is stored in persistent data storage. Writes made subsequent to the first backup to blocks not listed as free in the copy of the free block map as of the first time are tracked in a persistently-stored change block tracking log. A free block map as of a second time and the previously-stored copy of the free block map as of the first time are used to determine which blocks listed as free in the free block map as of the first time have been written to since the first time. At least a subset of blocks determined to have been written to since the first time are including in an incremental backup.

Abstract: A technique performs replication. The technique involves receiving, by processing circuitry, a virtual storage processor (VSP) replication command from a user. The VSP replication command specifies a source VSP and a destination VSP (e.g., configuration data which defines an operating environment). The technique further involves identifying, by the processing circuitry and in response to the VSP replication command, multiple source data objects which are configured to store data from the context of the source VSP. The technique further involves automatically creating, after the multiple source data objects are identified, multiple replication sessions to replicate the multiple source data objects as multiple destination data objects which are configured to store data from the context of the destination VSP. Once created, the entire lifecycle of the replication session occurs at the VSP level and replication of the internals of the VSP are entirely hidden from the end user.

Abstract: The disclosure is directed to replicating datasets between data storage servers in a distributed computer network synchronously and asynchronously (“the technology”). A replication interface receives a request from a client to store a dataset in the distributed computer network. The replication interface identifies a first set of storage servers that are within a halo defined by the client. The replication interface replicates the dataset to the first set of the storage servers synchronously, and a remaining set of the storage servers, e.g., storage servers that are outside of the halo asynchronously. The replication interface can perform the synchronous and asynchronous replication simultaneously. The halo can be determined based on various parameters, including a halo latency, which indicates a permissible latency threshold between the client and a storage server to which the dataset is to be replicated synchronously.

Abstract: A method for storing data in a data storage system by partitioning the data into a plurality of data chunks and generating representative data for each of the plurality of chunks by applying a predetermined algorithm to each chunk of the plurality of chunks. Subsequently, the representative data is compared and sorted. Representative data for base data chunks and representative data for other data chunks that can be stored relative to the base data chunks are identified by evaluating the sorted set of representative data. Finally, each of the other data chunks identified as those that can be stored relative to a base data chunk are stored in the data storage system as the difference between the data chunk and a base data chunk.

Abstract: Storage administrators would like to create snapshots of a storage array as frequently as possible, but too many concurrent snapshots can place an unnecessary load on the storage array. Described herein are techniques for scheduling snapshots on the storage array with the objective of minimizing the maximum number of simultaneous snapshots and/or temporally spacing apart snapshots from each other.

Abstract: According to certain aspects, a method can include receiving an indication that a restoration of a deduplication database using a secondary copy of a file associated with a secondary copy job is complete; retrieving a first data fingerprint from a data storage database, wherein the first data fingerprint is associated with the secondary copy job used to restore the deduplication database; retrieving a second data fingerprint from a deduplication database media agent, wherein the second data fingerprint is associated with the secondary copy job used to restore the deduplication database; comparing the first data fingerprint with the second data fingerprint to determine whether the first data fingerprint and the second data fingerprint match; and transmitting an instruction to the deduplication database media agent to rebuild the restored deduplication database in response to a determination that the first data fingerprint and the second data fingerprint do not match.

Abstract: A method for context transfer for data storage is disclosed. The method includes receiving, from an analysis environment, a request to load a data item for analysis, creating, based on the request, a task request including context information of the data item, transmitting the task request to a data manager environment, receiving, from the data manager environment, an approval of the task request based on the context information, and loading the data item in a master data store in response to the approval.

Abstract: Techniques to backup collaboration server data are disclosed. An indication to begin backup of a collaboration server dataset is received. An associated directory is walked in a prescribed order to divide the dataset into a prescribe number of approximately equal-sized subsets. A separate subset-specific thread is used to back up the subsets in parallel. In some embodiments in which the collaboration data is stored in multiple volumes, a volume-based approach is used to back up the volumes in parallel, e.g., one volume per thread. In some embodiments, transaction logs are backed up in parallel with volumes of collaboration data.

Abstract: Techniques to back up data are disclosed. In various embodiments, a copy of a free block map as of a first time associated with a first backup is stored in persistent data storage. Writes made subsequent to the first backup to blocks not listed as free in the copy of the free block map as of the first time are tracked in a persistently-stored change block tracking log. A free block map as of a second time and the previously-stored copy of the free block map as of the first time are used to determine which blocks listed as free in the free block map as of the first time have been written to since the first time. At least a subset of blocks determined to have been written to since the first time are including in an incremental backup.

Abstract: A computer management apparatus one embodiment includes a split component configured to split data into a plurality of data elements; a send component configured to send each one of the plurality of data elements to a different location selected from a plurality of locations in response to the split component splitting the data, wherein each data element is different; and a message component configured to send a message to each of the locations. A computer management apparatus in another embodiment includes a receive component configured to receive a first data element; an analyze component configured to recieve a message, wherein the message comprises an address of each of the further locations; and a send component configured to send the first data element to each of the further locations of the plurality of further locations in response to the analyze component determining the address of each of the further locations.

Abstract: A storage system according to certain embodiments includes a repository of client-side data block signature information representative of a set of data blocks stored in a primary storage subsystem. In some cases, the system sources data blocks for secondary copy and restore operations from the primary storage subsystem instead of the secondary storage subsystem. Where multiple primary storage components (e.g., multiple client computing devices) contain copies of a data blocks involved in a secondary copy or restore operation, the system can decide which client to source the data block from based on sourcing criteria.

Abstract: A storage system according to certain embodiments includes a client-side signature repository that includes information representative of a set of data blocks stored in primary storage. During restore operations, the system can use the client-side signature repository to identify data blocks located in primary storage. The system can also use the client-side signature repository to identify multiple locations within primary storage where instances of some of the data blocks to be restored are located. Accordingly, during a restore operation of one client computing device, the system can source a data block to be restored to the client computing device from another client computing device that is in primary storage.

Abstract: In one embodiment, a method for sharing bandwidth in a data processing system having a plurality of locations includes splitting data into a plurality of data elements, sending each one of the plurality of data elements to a different location selected from the plurality of locations, wherein each data element is different, and sending a message to each of the locations. In another embodiment, a method for sharing bandwidth in a data processing system having a plurality of locations, wherein the plurality of locations comprises a first location and plurality of further locations, includes receiving a first data element, receiving a message, wherein the message comprises an address of each of the further locations, and sending the first data element to each of the further locations of the plurality of further locations, responsive to determining the address of each of the further locations.

Abstract: Scheduling of backup jobs is optimized in accordance with a characteristic of the backup jobs. The characteristic of the backup jobs can take into account a number of the backup jobs that are stale. A stale backup job is a backup job in which no backed up data changed during a most recent performance of the backup job.

Abstract: The present invention is capable of determining the rights to a file based on providing a descriptor. The descriptor can be calculated using an algorithm, which may be cryptographic and/or non-cryptographic. The descriptor may further be based on the file contents, metadata of the file, other file data, or any combination thereof to uniquely identify the file in a shared file repository. Since the descriptor is generated based on file data it will be the same regardless of which user generates it. Accordingly, only one copy of the file needs to be maintained in the shared file repository, thereby reducing the amount of network bandwidth required to assure the file is backed up and further reducing the amount of storage required to backup the files. This results in a vastly more efficient method of backup in terms of processing time, network bandwidth, and storage requirements.