Alibaba Group Holding Limited

Lsi Corporation

Avago Technologies General IP (Singapore) Pte. Ltd.

Marvell International Limited

Seagate Technology Incorporated

Lumileds LLC

Alibaba Singapore Holding Private Limited

Marvellworld Trade Ltd.

Shu Li

Fan Zhang

Shaohua Yang

Jun Xiao

Ping Zhou

Haitao Xia

Chung-Li Wang

Panu Chaichanavong

Zongwang Li

Jianjian Huo

Fei Liu

Jun Gao

Naim Siemsen-Schumann

Sheng Qiu

Lu Lu

Yifei Zhang

Xiaowei Jiang

Yu Du

Bruce Alexander Wilson

Yang Han

Wei Liu

Anatoli Aleksandrovich Bolotov

Xuebin Wu

Wei Cao

Yu Chin Fabian Lim

Gongbiao Niu

Wei Zou

Rui Cao

George Mathew

Qi Qi

Yu Kou

Mikhail I Grinchuk

Jefferson E Singleton

Ming Lin

Xiang Wang

Qi Zuo

Kaitlyn T Nguyen

Han Fang

Yequn Zhang

Thuy Vu

Kuhong Jeong

Chaichanavong Panu

Sheng Qui

The present disclosure provides methods, systems, and non-transitory computer readable media for migrating data in a data storage system. A method for migrating data comprises: transferring data from a storage cluster in a first data center to a migration cartridge of the first data center; converting, by the migration cartridge of the first data center, the data's format into an archival format; storing the data into a media card; and moving the media card from the first data center to a second data center, wherein the data is read from the media card into a migration cartridge of the second data center and stored into an archival cluster in the second data center according to the archival format of the data.

Method and system of large amount of data migration with enhanced efficiency

The present disclosure provides storage nodes, integrated circuits, and methods for storage node management. A method for storage node management includes performing one or more network tasks by one or more first processing cores in a network engine of an integrated circuit; and performing one or more storage tasks by one or more second processing cores in a storage engine of the integrated circuit.

Storage nodes, integrated circuits and methods for storage node management

One embodiment facilitates measurement of a performance of a storage device. During operation, the system determines a normalized cost for an I/O request, wherein the normalized cost is independent of an access pattern and a type of the I/O request, wherein the normalized cost is indicated by a first number of virtual I/O operations consumed by the I/O request, and wherein a virtual I/O operation is used as a logical unit of cost associated with physical I/O operations. The system identifies a performance metric for the storage device by calculating a second number of virtual I/O operations per second which can be executed by the storage device. The system allocates incoming I/O requests to the storage device based on the performance metric, e.g., to satisfy a Quality of Service requirement, thereby causing an enhanced measurement of the performance of the storage device.

System and method for managing resources of a storage device and quantifying the cost of I/O requests

The present disclosure relates to a system and a method for data protection. In some embodiments, an exemplary method for data encoding includes: receiving a data bulk; performing an erasure coding (EC) encoding on the data bulk to generate one or more EC codewords; distributing a plurality of portions of each EC codeword of the one or more EC codewords across a plurality of solid-state drives (SSDs); performing, at each SSD of the plurality of SSDs, an error correction coding (ECC) encoding on portions of the one or more EC codewords distributed to the SSD to generate an ECC codeword; and storing, in each SSD of the plurality of SSDs, the ECC codeword.

System and method for data protection in solid-state drives

One embodiment described herein provides a distributed computing system. The distributed computing system can include a compute cluster comprising one or more compute nodes and a storage cluster comprising a plurality of storage nodes. A respective compute node can be configured to: receive a request for a computation task; obtain path information associated with data required by the computation task; identify at least one storage node based on the obtained path information; send at least one computation instruction associated with the computation task to the identified storage node; and receive computation results from the identified storage node subsequently to the identified storage node performing the computation task.

System and method for offloading computation to storage nodes in distributed system

The present disclosure provides methods, systems, and non-transitory computer readable media for optimizing data storing. An exemplary system comprises: a flash drive comprising a plurality of dies; and a memory configured to store a mapping associating a first virtual machine with a first set of dies of the plurality of dies and a second virtual machine with a second set of dies of the plurality of dies, wherein: the first set of dies are hibernated in response to the first virtual machine changing to an inactive state; and the first set of dies are activated in response to the first virtual machine changing to an active state.

Method and system of host resource utilization reduction

One embodiment provides a system which facilitates data management. During operation, the system processes, by a storage device, a write request and data associated with the write request, wherein the storage device comprises a plurality of channels over which to access a non-volatile memory of the storage device. The system writes the data to a first data buffer of the storage device while bypassing a first interface and a memory controller. The system sends the write request to the memory controller via the first interface. The system writes, via a first channel allocated for host write operations, the data from the first data buffer to the non-volatile memory. The system performs a garbage collection operation on the data, which comprises accessing the data via a second channel allocated for garbage collection operations.

Method and system for facilitating write latency reduction in a queue depth of one scenario

One embodiment provides a system which facilitates data management. The system receives, by a storage device via read requests from multiple streams, a first plurality of logical block addresses (LBAs) and corresponding stream identifiers. The system assigns a respective LBA to a first queue of a plurality of queues based on the stream identifier corresponding to the LBA. Responsive to determining that a second plurality of LBAs in the first queue are of a sequentially similar pattern: the system retrieves, from a non-volatile memory of the storage device, data associated with the second plurality of LBAs; and the system stores the retrieved data and the second plurality of LBAs in a volatile memory of the storage device while bypassing data-processing operations.

Method and system for facilitating multi-stream sequential read performance improvement with reduced read amplification

The present disclosure provides methods, systems, and non-transitory computer readable media for efficiently storing data. The methods include segmenting a parcel of data into one or more data chunks according to a physical block size of the secondary storage unit, wherein the one or more data chunks include a partial data chunk and zero or more full data chunks; sending each full data chunk of the zero or more full data chunks to the secondary storage unit to be written to a selected physical block of the secondary storage unit; collecting, in a collection buffer, the current partial data chunk and at least another partial data chunk; and sending a combination of the current partial data chunk and a subset of the plurality of other partial data chunks to the secondary storage unit to be written to a selected physical block of the secondary storage unit, wherein said combination fills substantially all of a physical-block-sized data chunk.

Methods and systems of efficiently storing data

One embodiment provides a system and method for reshaping the power budget of a cabinet to facilitate an improved deployment density of servers. A battery cabinet comprises: a plurality of sealed batteries; a power outlet; and a power management module coupled to the sealed batteries and the power outlet. The power management module comprises: a power monitoring module configured to monitor a first amount of power consumed by one or more computing devices via a main power supply; a detection module configured to detect that the first amount of power consumption exceeds a predetermined power consumption threshold; and a power provision module configured to provide, via the sealed batteries, power to the power outlet until the first amount of power consumption no longer exceeds the predetermined power consumption threshold.

System and method for reshaping power budget of cabinet to facilitate improved deployment density of servers

Embodiments of the disclosure provide systems and methods accessing a storage device of a host machine. The method can include: receiving, via a first guest flash translation layer (FTL) instance, a first request for accessing the storage device from a first virtual machine running on a host machine, wherein the first request comprises a first physical address of the storage device; transmitting, via the first FTL instance, the first request to a host FTL driver; converting, via the host FTL driver, the first request into a first hardware command; transmitting, via the host FTL driver, the first hardware command to the storage device; and executing, via the solid state drive, the first hardware command.

Open-channel storage device management with FTL on virtual machine

The present disclosure provides methods, systems, and non-transitory computer readable media for performing data transfers with improved error encoding. The methods include receiving a request for data transfer from a source medium in the data storage system to a destination medium in the data storage system, wherein the data storage system comprises a computer cluster and a storage cluster; determining whether the source medium and the destination medium are within the storage cluster; based on the determination of whether the source medium and the destination medium are within the storage cluster, transferring the data from the source medium to the destination medium, wherein: the data is transferred without performing error correcting code check when the data is transferred within the storage cluster, and the data is transferred with an error correcting code check when the data is transferred between the computer cluster and the storage cluster.

Method and system of deduplication of error codec in hyperscale infrastructure

During operation, a key-value storage system can receive a request to write data to a data region in a first non-volatile memory. The system can determine a key associated with the data and the key can correspond to an entry in a data structure maintained by a volatile memory the storage system. In response to determining the key, the system can write the data to the data region in the first non-volatile memory. The system can update in the volatile memory the data structure entry corresponding to the key with a physical location in the data region of the first non-volatile memory to which the data is written. The system can write the data structure update to a second non-volatile memory. The system can then store a snapshot of the data structure in a metadata region associated with the first non-volatile memory, thereby allowing persistent storage of the data structure.

System and method for facilitating improved performance in ordering key-value storage with input/output stack simplification

The present disclosure provides methods, systems, and non-transitory computer readable media for operating a cache drive in a data storage system. The methods include receiving, from an IO interface in the cache drive of the compute server, a write request to write data; caching the data corresponding to the write request in a cache storage of the cache drive of the compute server; performing one or more compute processes on the data; and in response to performing the one or more compute processes on the data, providing the processed data to a storage cluster for storing via the IO interface that is communicatively coupled to the storage cluster.

Method and system for condensed cache and acceleration layer integrated in servers

The system can receive data to be written to a non-volatile memory in the distributed storage system. The received data can include a plurality of input segments. The system can assign consecutive logical block addresses (LBAs) to the plurality of input segments. The system can then compress the plurality of input segments to generate a plurality of fixed-length compressed segments, with each fixed-length compressed segment aligned with a physical block address (PBA) in a set of PBAs. The system compresses the plurality of input segments to enable an efficient use of storage capacity in the non-volatile memory. Next, the system can write the plurality of fixed-length compressed segments to a corresponding set of PBAs in the non-volatile memory. The system can then create, in a data structure, a set of entries which map the LBAs of the input segments to the set of PBAs. This data structure can be used later by the system when processing a read request including a LBA.

System and method for facilitating mitigation of read/write amplification in data compression

Growing community of inventors

Bothell, WA, United States of America

Shu Li