Avago Technologies General IP (singapore) Pte. Ltd.

Lsi Corporation

Hewlett-packard Development Company, L.p.

Lsi Logic Corporation

Hewlett Packard Enterprise Development LP

Avago Technologies International Sales Pte. Limited

Sumanesh Samanta

Horia Cristian Simionescu

Luca Bert

Sujan Biswas

Kishore Kumar Muppirala

Mark Ish

Mohana Rao Goli

Paresh Chatterjee

Satish Kumar Mopur

Dinkar Sitaram

Parag Ranjan Maharana

Ayman Abouelwafa

Saugata Das Purkayastha

Karimulla Sheik

Debal Krishna Mridha

Ramkumar Venkatachalam

Arif Abdulhusein Merchant

Timothy E Hoglund

Mustafa Uysal

Basavaraj Gurupadappa Hallyal

Kishore Kaniyar Sampathkumar

Naveen Krishnamurthy

Narayanan Ananthakrishnan Nellayi

Srikanth Krishnamurthy

Philip K Wong

Sourav Saha

Allen Kelton

Satadal Bhattacharjee

Debal Kr Mridha

Naga S Vadalamani

Anirban Bhattacharyya

Srikanth Krishnamurthy Sethuramachar

A method for managing a pool buffers includes establishing a first buffer class with a first allowable number of buffers, and a first reserved number of buffers that are reserved for the first buffer class in the pool of buffers even if no Input/Output (I/O) operation is running in connection with the first buffer class. The method includes establishing a second buffer class with a second allowable number of buffers, and a second reserved number of buffers that are reserved for the second buffer class in the pool of buffers even if no I/O operation is running in connection with the second buffer class. The first buffer is enabled class to have more than the first allowable number of buffers as long as a number of buffers allocated to the second buffer class is fewer than the second allowable number of buffers.

Devices and methods for managing memory buffers

Embodiments herein provide for redundant data storage. One storage system includes first and second host systems each comprising a memory and a persistent storage device. The storage system also includes first and second storage controllers each comprising a memory (e.g., DRAM). The memory of the first storage controller is mapped to the memory of the first host system and the memory of the second storage controller is mapped to the memory of the second host system. The first storage controller is operable to DMA data from the persistent storage device of the first host system to the memory of the first storage controller, and to direct the second storage controller to DMA the data to the persistent storage device of the second host system via the memory of the second storage controller.

Data replication across host systems via storage controller

An apparatus having a cache and a controller is disclosed. The controller is configured to (i) gather a plurality of statistics corresponding to a plurality of requests made from one or more hosts to access a memory during an interval, (ii) store data of the requests selectively in the cache in response to a plurality of headers and (iii) adjust one or more parameters in the headers in response to the statistics. The requests and the parameters are recorded in the headers.

Self-adjusting caching system

Systems and methods maintain cache coherency between storage controllers using input/output virtualization. In one embodiment, a primary storage controller receives write commands over a virtualized interface, stores the write commands in cache memory, tracks a status of the write commands processed from the cache memory, and stores the status in a portion of the cache memory. A backup storage controller includes a backup cache that receives replications of the write commands via direct memory access operations, and stores the replications of the write commands. The primary storage controller makes the status available to a host system. In response to a failure of the primary storage controller, the backup storage synchronizes with the status from the host system, and resumes I/O operations for the logical volume.

Multi-node cache coherency with input output virtualization

Methods and structure for selective cache mirroring. One embodiment includes a control unit and a memory. The memory is able to store indexing information for a multi-device cache for a logical volume. The control unit is able to receive an Input/Output (I/O) request from a host directed to a Logical Block Address (LBA) of the logical volume, to consult the indexing information to identify a cache line for storing the I/O request, and to store the I/O request at the cache line on a first device of the cache. The control unit is further able to mirror the I/O request to another device of the cache if the I/O request is a write request, and to complete the I/O request without mirroring the I/O request to another device of the cache if the I/O request is a read request.

Selective mirroring in caches for logical volumes

Systems and methods to safely and efficiently handle dirty data flush are disclosed. More specifically, when a cache controller determines that one (or more) storage device of a cache device is running out of space, that storage device is given priority to be flushed prior to the other storage devices that are not in such a critical condition. In addition, a cache bypass process can be conditionally enabled to save free physical spaces already running low on such critical cache storage devices.

Safe and efficient dirty data flush for dynamic logical capacity based cache in storage systems

A storage subsystem can achieve more efficient I/O processing by enabling users to specify and pass out of band I/O hints comprising an object to be hinted, a hint type, and caching strategies associated with a hint type. A hinted object may be either a virtual device or a file. In addition to priority cache, hint types may include never-cache, sticky-cache, and volatile-cache. Hints may be passed via command-line or graphical-user interfaces.

Systems and methods for I/O processing using out-of-band hinting to block driver or storage controller

A system and method for managing the life expectancy of at least one solid state drive (SSD) within a cache device of a storage subsystem includes determining a baseline rate of decline for each SSD based on its guaranteed life expectancy. At intervals, each SSD of the cache device is polled for remaining life and power-on time, and a current rate of decline (based on time since initialization) and a cumulative rate of decline (based on total lifespan of the SSD) is determined. When both the current rate of decline and the cumulative rate of decline exceed the baseline rate of decline for any SSD of the cache device, write requests to that SSD are blocked and redirected to the virtual device until either the current rate of decline or cumulative rate of decline drop below the baseline rate.

System and method of life management for low endurance SSD NAND devices used as secondary cache

A system and method for managing cache memory of at least one node of a multiple-node storage cluster. A first cache data and a first cache metadata are stored for data transfers between a respective node and regions of a storage cluster receiving at least a first selected number of data transfer requests. When the node is rebooted, a second (new) cache data is stored to replace the first (old) cache data. The second cache data is compiled utilizing the first cache metadata to identify previously cached regions of the storage cluster receiving at least a second selected number of data transfer requests after the node is rebooted. The second selected number of data transfer requests is less than the first selected number of data transfer requests to enable a rapid build of the second cache data.

System and method of rebuilding READ cache for a rebooted node of a multiple-node storage cluster

The disclosure is directed to preserving data consistency in a multiple-node data storage system. According to various embodiments, a write log is maintained including log entries for data transfer requests being served by a respective node of the multiple-node data storage system. Rather than maintaining a full write journal of data and parity associated with each data transfer request, the log entries only need to identify portions of the virtual volume being updated according to the data transfer requests served by each node. When a first node fails, a second node takes over administration of a virtual volume for the failed node. Upon taking over for the first (failed) node, the second node resolves any inconsistencies between data and parity in portions of the virtual volume identified the respective log entries. Accordingly, write holes are prevented without substantially increasing memory usage or system complexity.

System and method of write hole protection for a multiple-node storage cluster

A method generates input/output (IO) commands by plural different applications that execute on a host. The method prioritizes the applications by inserting different classifiers into the IO commands at a host bus adapter (HBA) located in the host. A storage device receives the IO commands and processes the IO commands according to priorities based on the classifiers for the applications.

Prioritizing input/outputs at a host bus adapter

A method and system for IO processing in a storage system is disclosed. In accordance with the present disclosure, a controller may take long term 'lease' of a portion (e.g., an LBA range) of a virtual disk of a RAID system and then utilize local locks for IOs directed to the leased portion. The method and system in accordance with the present disclosure eliminates inter-controller communication for the majority of IOs and improves the overall performance for a High Availability Active-Active DAS RAID system.

Leased lock in active-active high availability DAS systems

Systems and methods presented herein provide for redundancy in I/O caching. In one embodiment, a storage controller includes a first cache operable to receive input/output requests between a host system and a storage device, to compress data of the input/output requests, and to cache the compressed data before writing to the storage device. The storage controller also includes a second cache operable to track chunks of the compressed data in the first cache. When the first cache fails, the second cache is operable to cache the tracked chunks of the compressed data that have not been written to the storage device in a third cache while leaving chunks of data in the second cache that have been written to the storage device.

Intelligent I/O cache rebuild in a storage controller

The disclosure is directed to a system and method for managing READ cache memory of at least one node of a multiple-node storage cluster. According to various embodiments, a cache data and a cache metadata are stored for data transfers between a respective node (hereinafter 'first node') and regions of a storage cluster. When the first node is disabled, data transfers are tracked between one or more active nodes of the plurality of nodes and cached regions of the storage cluster. When the first node is rebooted, at least a portion of valid cache data is retained based upon the tracked data transfers. Accordingly, local cache memory does not need to be entirely rebuilt each time a respective node is rebooted.

System and method of selective READ cache retention for a rebooted node of a multiple-node storage cluster

System and techniques for rebuilding a redundant secondary storage cache including a first storage device and a second storage device are described. A metadata entry indicative of a validity of a portion of information stored by a first storage cache device and associated with a region of a primary storage device is received. When the validity of the portion of information associated with the region of the primary storage device is established, a region lock is requested on the region of the primary storage device associated with the portion of information stored by the first storage cache device. Then, the portion of information and the corresponding metadata entry associated with the region of the primary storage device is copied from the first cache storage device to a second storage cache device to rebuild the second storage cache device.

Growing community of inventors

Bengaluru, India

Sumanesh Samanta