Abstract: A RAID controller includes a cache memory in which write cache blocks (WCBs) are protected by a RAID-5 (striping plus parity) scheme while read cache blocks (RCBs) are not protected in such a manner. If a received cache block is an RCB, the RAID controller stores it in the cache memory without storing any corresponding parity information. When a sufficient number of WCBs to constitute a full stripe have been received but not yet stored in the cache memory, the RAID controller computes a corresponding parity block and stores the RCBs and parity block in the cache memory as a single stripe.

Abstract: A data storage system is provided that implements a command-push model that reduces latencies. The host system has access to a nonvolatile memory (NVM) device of the memory controller to allow the host system to push commands into a command queue located in the NVM device. The host system completes each IO without the need for intervention from the memory controller, thereby obviating the need for synchronization, or handshaking, between the host system and the memory controller. For write commands, the memory controller does not need to issue a completion interrupt to the host system upon completion of the command because the host system considers the write command completed at the time that the write command is pushed into the queue of the memory controller. The combination of all of these features results in a large reduction in overall latency.

Abstract: A data storage system and methods for managing data to be transferred between a host and a data volume distributed across solid state storage modules are disclosed. A storage controller couples the host to the data volume and manages data transfers to and from the logical volume. The storage controller receives a set of parameters that define how an array of blocks and chunks of buffered data will be distributed across solid state storage modules. The storage controller receives and buffers data to be stored and transfers the same when the capacity of the buffered data will fill a set of arranged stripes in the defined array in a single write operation.

Abstract: A cache controller includes a cache memory distributed across multiple solid-state storage units in which cache line fill operations are applied sequentially in a defined manner and write operations are protected by a RAID-5 (striping plus parity) scheme upon a stripe reaching capacity. The cache store is responsive to data from a storage controller managing a primary data store. The cache store arranges the data differently based on the origin or type of data received at the cache interface. Line fill operations are placed in the cache memory without generating and storing corresponding parity information. When a sufficient number of write operations fill strips that constitute a full stripe are present in cache store, a corresponding parity strip is generated and stored in a strip location designated for storage of the parity information.

Abstract: A data storage system having a slow tier and a fast tier maintains hot data on the fast tier by migrating data from the slow tier to reserve space on the fast tier as data becomes hot over time. The system maintains a reserve space table and performs a mass migration of data from the fast tier to the slow tier. Data migration is frequently unidirectional with data migrating from the slow to the fast tier, reducing overhead during normal operation.

Abstract: A method for managing redundancy of data in a solid-state cache system including at least three solid-state storage modules. The method may include designating one or more extents of each dirty mirror pair to be of a particular priority order of at least two priority orders. The at least two priority orders can include at least a highest priority order. The highest priority order can have a higher relative priority than the other priority orders. The method may also include performing at least one redundancy conversion iteration. Each redundancy conversion iteration includes converting extents of at least two dirty mirror pairs into at least one RAID 5 group and at least one unconverted extent. The extents of the at least two dirty mirror pairs can include extents designated to be of a highest remaining priority order. Each redundancy conversion iteration can also include deallocating the at least one unconverted extent.

Abstract: An apparatus for elastic caching of redundant cache data. The apparatus may have a plurality of buffers and a circuit. The circuit may be configured to (i) receive a write request from a host to store write data in a storage volume, (ii) allocate a number of extents in the buffers based upon a redundant organization associated with the write request and (iii) store the write data in the number of extents, where (a) each of the number of extents is located in a different one of the buffers and (b) the number of extents are dynamically linked together in response to the write request.

Abstract: Disclosed is a process for determining a heat index for a block of data, such as an extent, for storage tiering. Weighted scores are used for read and write operations, since solid state devices operate better with read operations than write operations. The heat index associated with each extent is a function of a base score, rather than an absolute value. The base score is determined by adding the number of extents in a hot tier plus the access score, divided by the number of extents in the hot tier. In this fashion, the base score measures the weighted I/O activity relative to the size of the hot tier.

Abstract: A data storage system having a slow tier and a fast tier maintains hot data on the fast tier by migrating data from the slow tier to reserve space on the fast tier as data becomes hot over time. The system maintains a reserve space table and performs a mass migration of data from the fast tier to the slow tier. Data migration is frequently unidirectional with data migrating from the slow to the fast tier, reducing overhead during normal operation.

Abstract: A system and method for handling IO to drives in a RAID system is described. In one embodiment, the method includes providing a multiple disk system with a predefined strip size. IO request with a logical block address is received for execution on the multiple disk system. A cache line size from a plurality of cache line sizes is allocated, based on the available memory for allocation to cache line. A plurality of sub-IO requests with a sub-strip size is generated, where the sub-strip size is smaller than the strip size, based on the allocated cache line size. The generated sub-IO commands are executed on the multiple disk system.

Abstract: Disclosed is a process for determining a heat index for a block of data, such as an extent, for storage tiering. Weighted scores are used for read and write operations, since solid state devices operate better with read operations than write operations. The heat index associated with each extent is a function of a base score, rather than an absolute value. The base score is determined by adding the number of extents in a hot tier plus the access score, divided by the number of extents in the hot tier. In this fashion, the base score measures the weighted I/O activity relative to the size of the hot tier.

Abstract: A system and method for handling IO to drives in a RAID system is described. In one embodiment, the method includes providing a multiple disk system with a predefined strip size. IO request with a logical block address is received for execution on the multiple disk system. A cache line size from a plurality of cache line sizes is allocated, based on the available memory for allocation to cache line. A plurality of sub-IO requests with a sub-strip size is generated, where the sub-strip size is smaller than the strip size, based on the allocated cache line size. The generated sub-IO commands are executed on the multiple disk system.

Abstract: A method, apparatus, and system of improved handling of clustered media errors in raid environment are disclosed. In one embodiment, a method includes starting a command timer when a firmware accepts a command from a host, tracking an amount of time the command spends on handling of a clustered media error through the command timer, and stopping the command timer when at least one of the command is completed and a time limit expires. The method may complete a read as a success when a host IO is a read command. The method may complete a write as a success, after writing parity, and data when the host IO may be a write command.

Abstract: Methods and systems for bad data block management of redundant array of independent disks (RAID) are disclosed. In one embodiment, a method for managing a bad data block for a RAID includes filling a first logical block address (LBA) of a first disk having a media error using signature data, filling a second LBA of a second disk offlined from the RAID using the signature data, wherein the second LBA and the first LBA are on a same stripe of the RAID, storing the first LBA and the second LBA to a table in a disk data format (DDF) area associated with the first disk and the second disk, and computing and storing parity values for the stripe of the RAID associated with the first LBA and the second LBA based on data across the stripe.

Abstract: A method, apparatus, and system of improved handling of clustered media errors in raid environment are disclosed. In one embodiment, a method includes starting a command timer when a firmware accepts a command from a host, tracking an amount of time the command spends on handling of a clustered media error through the command timer, and stopping the command timer when at least one of the command is completed and a time limit expires. The method may complete a read as a success when a host IO is a read command. The method may complete a write as a success, after writing parity, and data when the host IO may be a write command.

Abstract: A system, apparatus and method for maintaining information related to a write operation is described. In one embodiment of the invention, a write journal is provided that contains a list of entries that store information related to active write operations so that a particular write may be restarted in order to correct an inconsistency. The journal may have a battery backed cache, in which data is stored prior to writing to a disk, which is provided power in the case of a power failure. The journal may be located in memory positioned at various locations within a system including on a controller card for a disk array system or on a motherboard of a host system.

Abstract: A system, apparatus and method for maintaining information related to a write operation is described. In one embodiment of the invention, a write journal is provided that contains a list of entries that store information related to active write operations so that a particular write may be restarted in order to correct an inconsistency. The journal may have a battery backed cache, in which data is stored prior to writing to a disk, which is provided power in the case of a power failure. The journal may be located in memory positioned at various locations within a system including on a controller card for a disk array system or on a motherboard of a host system.