Abstract: A data protection system includes a splitter configured to reduce latencies when splitting writes in a computing environment. The splitter captures a write and adds metadata to augment the write with virtual related information. The augmented data is provided to a smartNIC while the write is then processed in the IO stack. The smartNIC may have a volume only visible to the splitter. The smartNIC also includes processing power that allows data protection operations to be performed at the smartNIC rather than with the processing resources of the host.

Abstract: One example method includes performing delta operations to protect data. A delta queue is provided that allows a replica volume to be rolled forwards and backwards in time. When rolling the replica volume forward, an undo delta is created such that the replica volume can be moved backwards after being moved forward. When rolling the replica volume backwards, a forward delta is created such that the replica volume can be moved forwards after being moved backwards.

Abstract: Data protection operations including replication operations are disclosed. Virtual machines, applications, and/or application data are replicated according to at least one strategy. The replication strategy can improve performance of the recovery operation.

Abstract: On-the-fly point-in-time recovery operations are disclosed. During a recovery operation, the PiT being restored can be changed on-the-fly or during the existing recovery operation without restarting the recovery process from the beginning. In one example, this improves recovery time operation (RTO) and prevents aspects of the recovery operation to be avoided when changing to a different PiT.

Abstract: One example method includes intercepting an IO issued by an application, writing the IO and IO metadata to a splitter journal in NVM, forwarding the IO to storage, and asynchronous with operations occurring along an IO path between the application and storage, evacuating the splitter journal by sending the IO and IO metadata from the splitter journal to a replication site. In this example, sending the IO and IO metadata from the journal to the replication site does not increase a latency associated with the operations on the IO path.

Abstract: One example method includes intercepting an IO issued by an application, writing the IO and IO metadata to a splitter journal in NVM, forwarding the IO to storage, and asynchronous with operations occurring along an IO path between the application and storage, evacuating the splitter journal by sending the IO and IO metadata from the splitter journal to a replication site. In this example, sending the IO and IO metadata from the journal to the replication site does not increase a latency associated with the operations on the IO path.

Abstract: Methods and systems for managing distribution of inference models throughout a distributed system are disclosed. To manage distribution of inference models, a system may include a data aggregator and one or more data collectors. The data aggregator may obtain a threshold, the threshold indicating an acceptable inference error rate for an inference model. The data aggregator may obtain an inference model based on the threshold by training an inference model, performing a lookup in an inference model lookup table, or via other methods. The data aggregator may optimize the inference model to determine the minimum quantity of computing resources consumed by an inference model in order to generate inferences accurate within the threshold. In order to do so, the data aggregator may simulate the operation of more computationally-costly inference models and less computationally-costly inference models.

Abstract: Methods and systems for managing data collection are disclosed. A data aggregator may aggregate data collected by a data collector. To reduce computing resources used for aggregation, the data aggregator and data collector may use inferences provided by a twin inference model in place of data collected by the data collector rather than receiving copies of data from the data collector. Over time, the aggregated data may be revised using revised inference models that are revised using subsequently obtained data from the data collector. The revised inference models may be used to obtain revised inferences that may replace original inferences in the aggregated data. The revised inferences may be of higher accuracy due to differences in the data upon which the inference and revised inference models are based.

Abstract: Methods and systems for managing data collection are disclosed. A data aggregator may aggregate data collected by a data collector. To reduce computing resources used for aggregation, the data aggregator and data collector may implement a multi-stage data reduction processes to reduce the quantity of data transmitted for data aggregation purposes. The multi-stage data reduction process may include implementing twin inference models at the aggregator and collector, identifying relationships in the data collected by the data collector using feature relationship inference models, transmitting a portion of the collected data to the data aggregator and withholding a second portion of the collected data based on acceptable level of error for use of the collected data, and reconstructing the withheld portion of the collected data at the aggregator. The reconstructed portion of the collected data may include the acceptable level of error when compared to a corresponding portion of the collected data.

Abstract: Methods and systems for managing data aggregation in a distributed environment are disclosed. The data may be aggregated using twin inference models which may be used to reduce a quantity of data transmitted to aggregate the data. To obtain twin inference models, models may be trained which may consume computing resources. A computing resource cost for training the twin inference models may be estimated based on an estimated number of twin inferences models necessary to meet inference accuracy goals. A model training device that has an available quantity of computing resources sufficient to meet the computing resource cost may be obtained. The model training device may be used to train and distribute inference models for data aggregation purposes.

Abstract: Methods and systems for managing aggregation of data throughout a distributed environment are disclosed. To manage aggregation of data, a system may include a data aggregator and one or more data collectors. The data aggregator may obtain a threshold, the threshold indicating an acceptable error level associated with a downstream consumer of the aggregated data. The data aggregator may obtain the acceptable error level by simulating operation of the downstream consumer using synthetic data sets. The synthetic data sets may include different levels of error and, therefore, the data aggregator may determine a level of error that may impact the operation of the downstream consumer to an acceptable degree. In order to facilitate data aggregation, an inference model may be implemented that meets the threshold while consuming a minimum quantity of computing resources during operation.

Abstract: A primary storage array calculates signatures of chunks of production device data that are sent to a target device on a secondary storage array. The chunk signatures are sent to a signature device on the secondary storage array, where the chunk signatures are stored within the same LBA range on the signature device as their corresponding chunks are stored on the target device. Snaps of the target and signature device are created and associated as a snap pair. Later, the primary storage array calculates signatures of changed chunks of production device data that are sent to the target device. The changed chunk signatures are sent to the signature device. New snaps of the target and signature device are created and associated as a new snap pair. Chunk data is validated by calculating signatures of the chunks from the target device and comparing those signatures with the chunk signatures from the signature device.

Abstract: A data protection system configured to backup a time series database is provided. The data protection system may be integrated with or have access to consolidation policies of the time series database. The backup policy and backup retention policy are set by monitoring the consolidation policy and adjusting the backup policy to ensure that the data in the time series database is protected prior to being downscaled, discarded or otherwise consolidated.

Abstract: Data protection operations including replication operations that dynamically adapt a topology of replica virtual machines. A data protection system may implement a machine model that is trained using, as input, characteristics of virtual machines. When a failure is predicted, a topology of the replica virtual machines is changed. The topology may also change when changes in the environment are detected. The changes may include redistributing the protected applications to the replica virtual machines and/or scaling the replica virtual machines.

Abstract: One example method includes contacting, by a client, a service, receiving a credential from the service, obtaining trust information from a trust broker, comparing the credential with the trust information, and either connecting to the service if the credential and trust information match, or declining to connect to the service if the credential and the trust information do not match. Other than by way of the trust information obtained from the trust broker, the client may have no way to verify whether or not the service can be trusted.

Abstract: One example method includes performing delta operations to protect data. Each delta generated by a data protection operation includes data. The deltas are stored in a delta queue, when moving a current replica to another point in time represented by the selected delta in the delta queue, the deltas are processed so that all relevant data can be applied in a batch. This ensures that when the same extents are represented in multiple deltas, only the oldest version is applied to the replica volume to move the current replica to the selected point in time.

Abstract: Methods and systems for managing data collection in a distributed system are disclosed. The system may include a data aggregator and a data collector. The data aggregator may aggregate data collected by the data collector. To reduce the computing resources used to aggregate data, the data aggregator and data collector may implement a multi-stage data reduction processes to reduce the quantity of data transmitted for data aggregation purposes. The multi-stage data reduction process may include implementing twin inference models at the aggregator and collector, identifying relationships in the data collected by the data collector, transmitting a portion of the collected data to the data aggregator based on acceptable level of error for use of the collected data, and reconstructing the un-transmitted portion of the collected data at the aggregator. The reconstructed portion of the collected data may include the acceptable level of error.

Abstract: On-the-fly point-in-time recovery operations are disclosed. During a recovery operation, the PiT being restored can be changed on-the-fly or during the existing recovery operation without restarting the recovery process from the beginning. In one example, this improves recovery time operation (RTO) and prevents aspects of the recovery operation to be avoided when changing to a different PiT.

Abstract: A live image of a virtual machine is disclosed. When generating a live image, an image of a virtual machine is generated. A journal is also generated that starts before a start time of the image and ends after the start time of the image. A live image is then generated by synchronizing the start time of the image with the journal. This includes evaluating or analyzing the journal relative to the backup to determine or synchronize the start time relative to the entries in the journal.

Abstract: One example method includes encoding data as a polysaccharide structure, synthesizing the polysaccharide structure to create polysaccharide storage media that comprises the data, and storing the polysaccharide storage media. The example method may also include compressing the polysaccharide and storing the compressed data as a polysaccharide.