摘要:
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.
摘要:
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.
摘要:
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.
摘要:
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.
摘要:
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.
摘要:
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.
摘要:
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.
摘要:
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.
摘要:
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.
摘要:
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.