Pure Storage Assigned Twenty-Six Patents

Remote management of storage array
Pure Storage, Inc., Mountain View, CA, has been assigned a patent (10,560,517) developed by Hu, Jimmy T., Foster City, CA, Noonan, Terence W., Vadnais Heights, MN, Vachharajani, Neil A., Menlo Park, CA, and Zuo, Daquan, Mountain View, CA, for a “remote management of a storage array.“

The abstract of the patent published by the U.S. Patent and Trademark Office states: ”Managing a storage array includes: receiving, by a client-side array services module from a cloud-based security module through data communications on a wide area network, a token representing authentication of user credentials, and managing, by the client-side array services module, a storage array only through data communications on a local area network, including sending, to the storage array, the token with a management instruction.”

The patent application was filed on April 30, 2018 (15/966,891).

Updating distributed storage network software
Pure Storage, Inc., Mountain View, CA, has been assigned a patent (10,558,819) developed by Resch, Jason K., Chicago, IL, for “updating distributed storage network software.“

The abstract of the patent published by the U.S. Patent and Trademark Office states: ”A method begins by a management unit of a distributed storage network (DSN) sending a software update notice to a plurality of dispersed storage (DS) units, wherein the plurality of DS units supports a plurality of digital storage vaults, and wherein a set of DS units of the plurality of DS units supports a digital storage vault of the plurality of digital storage vaults. The method continues with a DS processing module determining an update strategy for updating software of the plurality of DS units such that at least a decode threshold number of DS units of the set of DS units is continually available to service access requests to the digital storage vault and updating the software of at least some of the plurality of DS units in accordance with the update strategy.”

The patent application was filed on May 13, 2019 (16/410,419).

Priority level adaptation in dispersed storage network
Pure Storage, Inc., Mountain View, CA, has been assigned a patent (10,558,592) developed by Dhuse, Greg R., Chicago, IL, for a “priority level adaptation in a dispersed storage network.“

The abstract of the patent published by the U.S. Patent and Trademark Office states: ”A processing system in a dispersed storage network is configured to access write sequence information corresponding to a write sequence, determine whether to elevate a priority level of the write sequence, when the processing system determines to elevate the priority level of the write sequence, elevate the priority level of the write sequence, determine whether to lower the priority level of the write sequence, and when the processing system determines to lower the priority level of the write sequence, the processing system lowers the priority level of the write sequence.”

The patent application was filed on February 28, 2019 (16/288,848).

Mediating between storage systems synchronously replicating dataset
Pure Storage, Inc., Mountain View, CA, has been assigned a patent (10,558,537) developed by Colgrove, John, Los Altos, CA, Gill, Thomas, Mountain View, CA, Grunwald, David, San Francisco, CA, Karr, Ronald, Palo Alto, CA, and Trivedi, Kunal, San Francisco, CA, for “mediating between storage systems synchronously replicating a dataset.“

The abstract of the patent published by the U.S. Patent and Trademark Office states: ”Mediating between storage systems synchronously replicating a dataset, including: requesting, by a first storage system in response to detecting a triggering event, a lock for a shared resource from a mediation service, requesting, by a second storage system in response to detecting the triggering event, the lock for the shared resource from the mediation service, and responsive to acquiring the lock from the mediation service, the first storage system, instead of the second storage system, processing data storage requests directed to the dataset that is synchronously replicated across the first storage system and the second storage system.”

The patent application was filed on September 13, 2017 (15/703,559).

Rebuilding strategy in memory managed multi-site duplication
Pure Storage, Inc., Mountain View, CA, has been assigned a patent (10,558,527) developed by Kazi, Asimuddin, Naperville, IL, and Resch, Jason K., Chicago, IL, for “rebuilding strategy in memory managed multi-site duplication.“

The abstract of the patent published by the U.S. Patent and Trademark Office states: ”A method includes identifying encoded data slices in need of rebuilding, where the encoded data slices are of plurality of copies of a set of encoded data slices stored in a plurality of sets of storage units of a plurality of dispersed storage network (DSN) memories. The method further includes determining a rebuilding strategy for the encoded data slices in need of rebuilding based on at least one of an urgency rebuild factor and a rebuild complexity factor. For a first encoded data slice of the encoded data slices in need of rebuilding, the method includes implementing a rebuild of the first encoded data slice in accordance with the rebuilding strategy to produce a rebuilt first encoded data slice, and sending the rebuilt first encoded data slice to a first storage unit of one of the plurality of sets of storage units.”

The patent application was filed on December 12, 2017 (15/839,254).

Solid state drives with multiple types of addressable memory
Pure Storage, Inc., Mountain View, CA, has been assigned a patent (10,552,090) developed by Karr, Ronald, Palo Alto, CA, Miller, Ethan, Santa Cruz, CA, and Sapuntzakis, Constantine, Mountain View, CA, for “solid state drives with multiple types of addressable memory.“

The abstract of the patent published by the U.S. Patent and Trademark Office states: ”Solid state drives with multiple types of addressable memory, where the solid state drives include: a first memory component comprising a plurality of nonvolatile registers, a second memory component comprising flash memory, and one or more controllers configured to: receive a write operation, wherein the write operation indicates a first portion of data to be written to the flash memory and indicates a second portion of data to be written to one or more of the plurality of registers, and atomically write the first portion of the data to the flash memory and the second portion of the data to the one or more of the plurality of registers.”

The patent application was filed on September 7, 2017 (15/697,540).

Replication to cloud
Pure Storage, Inc., Mountain View, CA, has been assigned a patent (10,545,987) developed by Borowiec, Benjamin, Santa Clara, CA, Miller, Ethan L., Santa Cruz, CA, Hodgson, Steve, Bernat, Andrew R., Mountain View, CA, Ramanarayanan, Ganesh, Menlo Park, CA, Sharpe, Malcolm, Mountain View, CA, and Driscoll, Alan S., Fremont, CA, for a “replication to the cloud.“

The abstract of the patent published by the U.S. Patent and Trademark Office states: ”Systems, methods, and computer readable storage mediums for replicating data to the cloud. A first dataset is replicated from a first storage subsystem to the cloud, with only the changes made to the first dataset since a previous replication event being replicated to the cloud. Additionally, the data may be deduplicated and compressed before being replicated from the first storage subsystem to the cloud. In some cases, the first dataset may be replicated to the cloud in a stream format which is not directly usable and then, at a later point in time, loaded onto a second storage subsystem from the cloud.”

The patent application was filed on December 19, 2014 (14/577,110).

Distributed integrated high-speed solid-state non-volatile random-access memory
Pure Storage, Inc., Mountain View, CA, has been assigned a patent (10,545,861) developed by Dreier, Roland, Mountain View, CA, Karr, Ronald, Palo Alto, CA, and Kirkpatrick, Peter E., Mountain View, CA, for a “distributed integrated high-speed solid-state non-volatile random-access memory.“

The abstract of the patent published by the U.S. Patent and Trademark Office states: ”A system may include embedded storage devices, each including: a first solid state drive (SSD) storage portion and a second non-volatile random-access memory (NVRAM) portion. The NVRAM portion includes a random access memory (RAM) device, a processing device, and an energy source, where the first SSD portion and the second NVRAM portion are separately addressable. The system further includes a storage system controller, operatively coupled to the embedded storage devices via a network. The storage system controller may be to: determine that data is to be stored in the first SSD storage portion of a first embedded storage device of the plurality of embedded storage devices, and buffer the data in the second NVRAM portion of a second embedded storage device of the plurality of embedded storage devices.”

The patent application was filed on April 28, 2017 (15/582,395).

Data rebuild when changing erase block sizes during drive replacement
Pure Storage, Inc., Mountain View, CA, has been assigned a patent (10,545,687) developed by Bernat, Andrew R., Brennan, Timothy W., McAuliffe, Mark L.,and Vachharajani, Neil Buda, Mountain View, CA, for a “data rebuild when changing erase block sizes during drive replacement.“

The abstract of the patent published by the U.S. Patent and Trademark Office states: ”A method for rebuilding data when changing erase block sizes in a storage system is provided. The method includes determining one or more erase blocks to be rebuilt and allocating one or more replacement erase blocks, wherein the one or more erase blocks and the one or more replacement erase blocks have differing erase block sizes. The method includes mapping logical addresses, for the one or more erase blocks, to the one or more replacement erase blocks and rebuilding the one or more erase blocks into the one or more replacement erase blocks, in accordance with the mapping.”

The patent application was filed on October 31, 2017 (15/799,955).

Providing high availability to client-specific applications executing in storage
Pure Storage, Inc., Mountain View, CA, has been assigned a patent (10,545,676) developed by Colgrove, John, Los Altos, CA, Do, Lydia, Raleigh, NC, Miller, Ethan, Santa Cruz, CA, and Noonan, Terence, Vadnais Heights, MN, for “providing high availability to client-specific applications executing in a storage system.“

The abstract of the patent published by the U.S. Patent and Trademark Office states: ”Deploying client-specific applications in a storage system utilizing redundant system resources, including: identifying a redundant controller in the storage system, wherein the storage system includes at least a first controller and the redundant controller, and executing one or more applications on the redundant controller, wherein the one or more applications are executed in a container.”

The patent application was filed on October 9, 2017 (15/727,962).

Data object attribute based event detection in storage
Pure Storage, Inc., Mountain View, CA, has been assigned a patent (10,540,343) developed by Colgrove, John, Los Altos, CA, Hasbani, Joseph S., Hayes, John Martin, Mountain View, CA, Miller, Ethan L., Santa Cruz, CA, and Sandvig, Cary A., San Jose, CA, for a “data object attribute based event detection in a storage system.“

The abstract of the patent published by the U.S. Patent and Trademark Office states: ”System and methods for detecting events based on data object attributes in a storage system are described.”

The patent application was filed on August 27, 2018 (16/114,027).

Providing active/active front end by coupled controllers in storage
Pure Storage, Inc., Mountain View, CA, has been assigned a patent (10,540,307) developed by Dreier, Roland, Liu, Yan, Mountain View, CA, and Mann, Sandeep, Fremont, CA, for “providing an active/active front end by coupled controllers in a storage system.“

The abstract of the patent published by the U.S. Patent and Trademark Office states: ”Emulating a remote direct memory access (RDMA) link between controllers in a storage array, including: inserting, into a buffer utilized by a direct memory access (DMA) engine of a first storage array controller, a data transfer descriptor describing data stored in memory of the first storage array controller and a location to write the data to memory of the second storage array controller, retrieving, in dependence upon the data transfer descriptor, the data stored in memory of the first storage array controller, and writing the data into the memory of the second storage array controller in dependence upon the data transfer descriptor.”

The patent application was filed on March 5, 2018 (15/912,051).

Providing high availability to client-specific applications executing in storage
Pure Storage, Inc., Mountain View, CA, has been assigned a patent (10,545,676) developed by Colgrove, John, Los Altos, CA, Do, Lydia, Raleigh, NC, Miller, Ethan, Santa Cruz, CA, and Noonan, Terence, Vadnais Heights, MN, for “providing high availability to client-specific applications executing in a storage system.“

The abstract of the patent published by the U.S. Patent and Trademark Office states: ”Deploying client-specific applications in a storage system utilizing redundant system resources, including: identifying a redundant controller in the storage system, wherein the storage system includes at least a first controller and the redundant controller, and executing one or more applications on the redundant controller, wherein the one or more applications are executed in a container.”

The patent application was filed on October 9, 2017 (15/727,962).

Data object attribute based event detection in storage
Pure Storage, Inc., Mountain View, CA, has been assigned a patent (10,540,343) developed by Colgrove, John, Los Altos, CA, Hasbani, Joseph S., Hayes, John Martin, Mountain View, CA, Miller, Ethan L., Santa Cruz, CA, and Sandvig, Cary A., San Jose, CA, for a “data object attribute based event detection in a storage system.“

The abstract of the patent published by the U.S. Patent and Trademark Office states: ”System and methods for detecting events based on data object attributes in a storage system are described.”

The patent application was filed on August 27, 2018 (16/114,027).

Providing active/active front end by coupled controllers in storage
Pure Storage, Inc., Mountain View, CA, has been assigned a patent (10,540,307) developed by Dreier, Roland, Liu, Yan, Mountain View, CA, and Mann, Sandeep, Fremont, CA, for “providing an active/active front end by coupled controllers in a storage system.“

The abstract of the patent published by the U.S. Patent and Trademark Office states: ”Emulating a remote direct memory access (RDMA) link between controllers in a storage array, including: inserting, into a buffer utilized by a direct memory access (DMA) engine of a first storage array controller, a data transfer descriptor describing data stored in memory of the first storage array controller and a location to write the data to memory of the second storage array controller, retrieving, in dependence upon the data transfer descriptor, the data stored in memory of the first storage array controller, and writing the data into the memory of the second storage array controller in dependence upon the data transfer descriptor.”

The patent application was filed on March 5, 2018 (15/912,051).

Garbage collection for stable data
Pure Storage, Inc., Mountain View, CA, has been assigned a patent (10,540,095) developed by Cheng, Huihui, Fremont, CA, Dang, Gunjan, Sunnyvale, CA, Goldsby, Michael, San Francisco, CA, Jiang, Yanwei, Sunnyvale, CA, Karumbunathan, Aswin, San Francisco, CA, Kirkpatrick, Pete, Neelakantam, Naveen, Mountain View, CA, Vachharajani, Neil Buda, San Francisco, CA, and Zhu, Junming, Mountain View, CA, for an “efficient garbage collection for stable data.“

The abstract of the patent published by the U.S. Patent and Trademark Office states: ”A storage controller coupled to a storage array comprising one or more storage devices performs a uniform sampling of data storage items in an append-only file system to identify a sample set and identifies at least two data storage item groups based on an age of the data storage items. The storage controller performs a garbage collection process on the append-only file system to identify stale data storage items in a first logical storage segment and active data storage items in the first logical storage segment and writes a first active data storage item associated with a first group of the two data storage item groups from the first logical storage segment to a second logical storage segment, the second logic storage segment comprising other active data storage items associated with the first group.”

The patent application was filed on January 26, 2017 (15/416,385).

Providing high availability for applications executing on storage
Pure Storage, Inc., Mountain View, CA, has been assigned a patent (10,534,677) developed by Curley, Jonathan, Menlo Park, CA, Jin, Yuchen, San Jose, CA, Lumb, Christopher, San Francisco, CA, Potashnik, Alexei, Palo Alto, CA, Uppugandla, Dilip Kumar, Milpitas, CA, Zankel, Christian, Sunnyvale, CA, and Zheng, Xiaojing, San Jose, CA, for “providing high availability for applications executing on a storage system.“

The abstract of the patent published by the U.S. Patent and Trademark Office states: ”Migrating applications executing on a storage system, including: detecting, by the storage system, that an application executing on a first platform within the storage system should be migrated to a second platform within the storage system, rejecting, by the storage system, all pending input/output (I/O) requests received by the storage system from the application executing on the first platform, and initiating, by the storage system, execution of the application on the second platform.”

The patent application was filed on March 1, 2018 (15/909,538).

Accessing data in dispersed storage network
Pure Storage, Inc., Mountain View, CA, has been assigned a patent (10,534,668) developed by Wozniak, Ethan S., Park Ridge, IL, Baptist, Andrew D., Mt. Pleasant, WI, Dhuse, Greg R., Volvovski, Ilya, and Resch, Jason K., Chicago, IL, for “accessing data in a dispersed storage network.“

The abstract of the patent published by the U.S. Patent and Trademark Office states: ”A method for execution by a computing device includes generating a data segment to include a first data object for storage and a plurality of null data objects. The data segment is dispersed storage error encoded to produce a set of encoded data slices that includes a first encoded data slice that corresponds to the first data object, a plurality of null slices corresponding to the null data objects, and a remaining number of error coded slices. Storage of the set of encoded data slices in a set of storage units is facilitated. Storage of a second data object is facilitated, where one null data object is overwritten with the second data object. A partial contribution of the second data object is calculated for each of the error coded slices in accordance with a partial encoding approach. Each error coded slice is updated by utilizing the corresponding partial contribution.”

The patent application was filed on December 5, 2017 (15/832,391).

Selecting storage error abatement alternative in dispersed storage network
Pure Storage, Inc., Mountain View, CA, has been assigned a patent (10,534,661) developed by Resch, Jason K., Chicago, IL, for “selecting a storage error abatement alternative in a dispersed storage network.“

The abstract of the patent published by the U.S. Patent and Trademark Office states: ”A method for execution by an integrity processing unit includes detecting a storage error associated with storage of at least one encoded data slice in at least one memory of an associated storage unit of a set of storage units. Error parameters associated with the storage error are determined and a plurality of recovery alternatives to abate the storage error are identified based on the error parameters. A plurality of cost-benefit factors that correspond the plurality of recovery alternatives are determined. One of the plurality of recovery alternatives is selected based on the plurality of cost-benefit factors, and execution of the one of the plurality of recovery alternatives is facilitated to abate the storage error.”

The patent application was filed on December 15, 2017 (15/843,390).

Resource utilization balancing
Pure Storage, Inc., Mountain View, CA, has been assigned a patent (10,534,648) developed by Frandzel, Yuval, Foster City, CA, and Vijayasankar, Kiron, Santa Clara, CA, for a “system resource utilization balancing.“

The abstract of the patent published by the U.S. Patent and Trademark Office states: ”Ensuring the fair utilization of system resources using workload based, time-independent scheduling, including: determining whether an amount of system resource utilization in the storage system has reached a predetermined utilization threshold, and responsive to determining that the amount of system resource utilization in the storage system has reached a predetermined utilization threshold: determining whether one or more entities in the storage system have utilized system resources in excess of their fair share by a predetermined threshold during a time-independent period, and responsive to determining that one or more entities in the storage system have utilized system resources in excess of their fair share by the predetermined threshold during the time-independent period, freezing, at least partially, an amount by which the one or more entities in the storage system have utilized system resources in excess of their fair share.”

The patent application was filed on December 20, 2016 (15/385,030).

Determining slices to rebuild from low-level failures
Pure Storage, Inc., Mountain View, CA, has been assigned a patent (10,530,862) developed by Isely, Michael Christian, Batavia, IL, and Resch, Jason K., Chicago, IL, for “determining slices to rebuild from low-level failures.“

The abstract of the patent published by the U.S. Patent and Trademark Office states: ”A distributed storage network (DSN) includes multiple distributed storage task execution (DST EX) units, each employing multiple memory portions to store encoded data slices. A DST EX unit detects a physical storage failure associated with an affected memory portion of a storage unit included in the DST EX unit. A memory portion identifier of the affected memory portion is used to identify a range of impacted encoded data slices associated with the affected memory portion, and in some cases specific encoded data slices within that range. The DST Ex unit issues rebuilding information to the DSN. The rebuilding information includes at least one identifier associated with at least one impacted encoded data slice included in the range of impacted encoded data slices.”

The patent application was filed on December 20, 2017 (15/848,196).

Utilizing multiple storage pools in dispersed storage network
Pure Storage, Inc., Mountain View, CA, has been assigned a patent (10,530,861) developed by Wozniak, Ethan S., Park Ridge, IL, Baptist, Andrew D., Mt. Pleasant, WI, Dhuse, Greg R., Volvovski, Ilya, Resch, Jason K., Chicago, IL, and Cocagne, Thomas D., Elk Grove Village, IL, for “utilizing multiple storage pools in a dispersed storage network.“

The abstract of the patent published by the U.S. Patent and Trademark Office states: ”A method for execution by a dispersed storage and task (DST) processing unit includes receiving data for storage. A storage approach for the data is determined based on the data. Storage of the data in a plurality of sets of storage units is facilitated in accordance with the storage approach. A determination is made to recover the data from storage, and a set of storage units is selected from the plurality of sets of storage units for recovery of the data. Recovery of the data from the selected set of storage units is facilitated.”

The patent application was filed on November 20, 2017 (15/818,633).

Transitioning to optimized data storage approach in dispersed storage network
Pure Storage, Inc., Mountain View, CA, has been assigned a patent (10,528,425) developed by Wozniak, Ethan S., Park Ridge, IL, Baptist, Andrew D., Mt. Pleasant, WI, Dhuse, Greg R., Volvovski, Ilya, Resch, Jason K., Chicago, IL, Khadiwala, Ravi V., Bartlett, IL, and Leggette, Wesley B., Chicago, IL, for “transitioning to an optimized data storage approach in a dispersed storage network.“

The abstract of the patent published by the U.S. Patent and Trademark Office states: ”A method for execution by a computing device includes dispersed storage error encoding a data segment to produce a set of encoded data slices in accordance with an information dispersal algorithm, (IDA) width number. Storage of the set of encoded data slices in a set of storage units is maintained. Activation of an incremental subset of storage units is detected to produce an expanded set of storage units in accordance with an updated IDA width number. An incremental subset of encoded data slices of an expanded set of encoded data slices is generated in accordance with the updated IDA width number. Storage of the expanded set of encoded data slices in the expanded set of storage units is maintained. A write threshold number is updated to produce an updated write threshold number. Storage of the updated write threshold number of the expanded set of encoded data slices is maintained.”

The patent application was filed on December 12, 2017 (15/839,192).

Mapping around defective flash memory of storage array
Pure Storage, Inc., Mountain View, CA, has been assigned a patent (10,528,419) developed by Davis, John D., Hayes, John, Kannan, Hari, Miladinovic, Nenad, and Tan, Zhangxi, Mountain View, CA, for a “mapping around defective flash memory of a storage array.“

The abstract of the patent published by the U.S. Patent and Trademark Office states: ”A method of failure mapping is provided. The method includes determining that a non-volatile memory block in the memory has a defect and generating a mask that indicates the non-volatile memory block and the defect. The method includes reading from the non-volatile memory block with application of the mask, wherein the reading and the application of the mask are performed by the non-volatile solid-state storage.”

The patent application was filed on September 15, 2017 (15/705,691).

Modifying and utilizing file structure in dispersed storage network
Pure Storage, Inc., Mountain View, CA, has been assigned a patent (10,528,282) developed by Kaczmarek, Joseph M., Chicago, IL, Wozniak, Ethan S., Park Ridge, IL, and Volvovski, Ilya, Chicago, IL, for “modifying and utilizing a file structure in a dispersed storage network.“

The abstract of the patent published by the U.S. Patent and Trademark Office states: ”A method for execution by a storage unit of a dispersed storage network includes receiving a slice access request that includes a slice name. A first function is performed on the slice name to produce a bucket file identifier. A second function is performed on the slice name to produce a bucket identifier. A bucket file of a plurality of bucket files is accessed, where the bucket file is identified by utilizing the bucket file identifier. A bucket of a plurality of buckets within the bucket file is accessed, where the bucket is identified by utilizing the bucket identifier. It is determined to modify a number of buckets in the bucket file based on bucket utilization. An attribute of the second function is modified in response, where the attribute is associated with the number of buckets in the bucket file.”

The patent application was filed on December 14, 2017 (15/842,596).

Tombstones for no longer relevant deduplication entries
Pure Storage, Inc., Mountain View, CA, has been assigned a patent (10,528,280) developed by Sandvig, Cary A., Palo Alto, CA, Sapuntzakis, Constantine P., Mountain View, CA, and Wang, Feng, Sunnyvale, CA, for “tombstones for no longer relevant deduplication entries.“

The abstract of the patent published by the U.S. Patent and Trademark Office states: An implementation of the disclosure provides a system comprising a storage array comprising a plurality of data blocks and a storage controller coupled to the storage array. The storage controller comprising a processing device to identify a canonical instance of a data block in a vector associated with a deduplication map. The vector represents a plurality of updates to the deduplication map over a determined time period. A deduplication reference representing duplicate data of the data block in the storage array is select from the deduplication map. The deduplication reference is remapped in the deduplication map to point to the canonical instance. Based on the remapping, an entry in the deduplication map for the deduplication reference is updated with a record. Responsive to detecting that the entry is in a location associated with an original entry of the data block in the deduplication map, delete the entry with the record.”

The patent application was filed on January 31, 2017 (15/420,726).