Speichergerät und Verfahren zu seiner Steuerung

Data storage system with parity reads and writes only on operations requiring parity information

Storage system and control method thereof

NONVOLATILE MEDIA DIRTY REGION TRACKING

Raid level 5 with free blocks parity cache

A system for writing data to a disk array includes a cache memory coupled to the disk array for storing data indicative of locations on the disk array and parity blocks associated with parity groups including the locations. Each of the parity blocks includes an identifier indicative of locations within a particular parity group which are protected by the parity data. Write logic reads the identifier from the parity block, and based thereon, determines whether a disk location is not protected by the parity data. The write logic also writes to the location and updates the parity data and the identifier associated with the parity block to include the location of the data block to indicate that the location is protected.

Disk array system based on disks with a fixed-length unit of access

Conventional methods for appending a validation code are not applicable to a disk array system in which the disk array comprises disk devices having a fixed sector length. The present invention solves this problem by separating validation codes from data blocks, bundling them together in blocks that can be easily matched with sectors, and carrying out all the associated management and control by hardware, such as coordination between validation codes and data blocks and operations of reading from and writing into the disk devices, thereby offering the same level of reliability as with conventional systems.

Storage system and data storage method

The storage system includes a first memory device configured to store data sent from a host system, a first memory device controller configured to control read/write access of the data from/to the first memory device, an arithmetic circuit unit configured to calculate parity data based on the data, a second memory device configured to store the parity data, a second memory device controller configured to control read/write access of the parity data from/to the second memory device. With this storage system, read access speed of the first memory device is faster than read access speed of the second memory device.

Implementing storage adapter performance optimization with enhanced hardware and software interface

A method and controller for implementing storage adapter performance optimization with chained hardware operations and an enhanced hardware (HW) and firmware (FW) interface minimizing hardware and firmware interactions, and a design structure on which the subject controller circuit resides are provided. The controller includes a plurality of hardware engines; and a processor. A data store is configured to store a plurality of control blocks. A global work queue includes a plurality of the control blocks selectively arranged in a predefined chain to define sequences of hardware operations. The global work queue includes a queue input coupled to the processor and the hardware engines and an output coupled to the hardware engines. The control blocks are arranged in respective engine work queues designed to control hardware operations of the respective hardware engines and respective control blocks are arranged in an event queue to provide completion results to the processor.

Methods and systems for using a write cache in a storage system

Methods and systems for storing data at a storage device of a storage system are provided. The data is first temporarily stored at a first write cache and an input/output request for a persistence storage device used as a second write cache is generated, when an I/O request size including the received data has reached a threshold value. The data from the first cache is transferred to the persistence storage device and a recovery control block with a location of the data stored at the persistence storage device is updated. An entry is added to a linked list that is used to track valid data stored at the persistence storage device and then the data is transferred from the persistence storage device to the storage device of the storage system.

MULTI-LEVEL DISK FAILURE PROTECTION

According to an embodiment of the invention there may be provided a method for multi-level disk failure protection, the method may include: calculating first parity information by processing a first data entity that is cached in a cache memory of a storage system thereby providing a first level of disk failure protection; destaging the first data entity and the first parity information to first physical addresses mapped to multiple disks; calculating extra parity information by processing the first data entity, wherein a combination of the first and extra parity information provides an extra level of disk failure protection that exceeds the first level of disk failure protection; and destaging the extra parity information to at least one second physical address that differ from the first physical addresses, the at least one second physical address are included in a spare physical memory space that is not allocated, at a time of the destaging of the extra parity information, for storing data. 1. A method for multi-level disk failure protection , the method comprises:calculating first parity information by processing a first data entity that is cached in a cache memory of a storage system thereby providing a first level of disk failure protection;destaging the first data entity and the first parity information to first physical addresses mapped to multiple disks;calculating extra parity information by processing the first data entity, wherein a combination of the first and extra parity information provides an extra level of disk failure protection that exceeds the first level of disk failure protection; anddestaging the extra parity information to at least one second physical address that differ from the first physical addresses, the at least one second physical address are included in a spare physical memory space that is not allocated, at a time of the destaging of the extra parity information, for storing data.21. The method according to wherein the calculating of ...

Storage sub-system having expanded data read

A storage sub-system employs a staging control information table by which staging of data to be read and redundant data thereof can be executed together to reduce response time in the event of a data read failure. The staging control information table also permits pre-read staging to be executed in the forward, backward or both the forward and backward directions, to reduce response time.

Speicherplattenanordnung mit auf einer Vielzahl von Leiterplatten verteilten Speicherplatten, die bei einer Entfernung eines Teils der Leiterplatten zugänglich bleiben

Parity calculation for raid write cache

DEVICE OF STORAGE IN NETWORK

Network file storage system includes local logical fileserver managing redundancy system and provided access via Internet to remote storage

Ce dispositif de stockage en réseau comporte un système comprenant un serveur de fichiers, un pilote de volumes logiques, un dispositif de cache et un pilotede volumes redondants connecté à une pluralité de dispositifs de blocs en réseau de façon à fournir un moyen de partager en toute sécurité et sans limites de capacité des fichiers sur un réseau ou au sein d'un micro-ordinareur.

Storage system realizing scalability and fault tolerance

A storage system to be connected to a large-scale computer includes a plurality of first logical units connected to a host device, a plurality of second logical units connected to a storage device, a plurality of cache memories, and a common bus wired between these logical units and memories. The plurality of first logical units, the plurality of second logical units, and the plurality of cache memories are all made in the form of modules. The modules are detachably mounted to the common bus disposed on a back plane. The storage device can be made up of a plurality of small-size storage units arranged in an array. Thus, the storage system realizes its scalability. Since the plurality of first logical units, the plurality of second logical units, and the plurality of cache memories are duplexed and the common bus is made in the form of 2 channels, the storage system can perform degrade operation. Since plurality of first logical units, the plurality of second logical units, and the plurality ...

STORING DATA ON STORAGE NODES

Data management architecture

Nonvolatile media dirty region tracking

A storage set (e.g., an array of hard disk drives) may experience a failure, such as a loss of power, a software crash, or a disconnection of a storage device, while writes to the storage set are in progress. Recover from the failure may involve 5 scanning the storage set to detect and correct inconsistencies (e.g., comparing mirrors of a data set or testing checksums). However, lacking information about the locations of pending writes to the storage set during the failure, this "cleaning" process may involve scanning the entire storage set, resulting in protracted recovery processes. Presented herein are techniques for tracking writes to the 10 storage set by apportioning the storage set into regions of a region size (e.g., one gigabyte), and storing on the nonvolatile storage medium descriptors of "dirty" regions comprising in-progress writes. The post-failure recovery process may then be limited to the regions identified as dirty. Fig. 4 400 106 - 106 - 408 402 - ~ 108 DISK 1 108 DISK ...

Nonvolatile media dirty region tracking

SAFE WRITE TO MULTIPLY-REDUNDANT STORAGE

An arrangement of apparatus for safely writing data and parity to multiply-redundant storage comprises a first storage component operable to store at least a first mark in a storage device to index uniquely a pattern to be written by at least a data write; a write component operable to perform the at least data write; a further storage component operable to overwrite a mark in the storage device with at least a further mark to index uniquely a pattern to be written by a parity write; and a further write component operable to perform the parity write. Preferably, the first storage component comprises a second storage component operable to overwrite said at least first mark in said storage device with a second mark to index a pattern to be written by a first parity write; and the write component is further operable to perform the first parity write.

Methods and structure to maintain a two level cache in a RAID controller and thereby selecting a preferred posting method

Methods and associated data structures operable in a RAID subsystem to improve I/O performance. A two level cache data structure and associated methods are implemented with a RAID controller. The lower level cache comprises buffers holding recently utilized blocks of the disk devices. The upper level cache records which blocks are present in the lower level cache for each stripe in the RAID level 5 configuration. The upper level cache serves to reduce the overhead processing required of the RAID controller to determine which blocks are present in the lower level cache. Having more rapid access to this information by lowering the processing overhead enables the present invention to rapidly select between different write techniques to post data and error blocks from low level cache to the disk array. A RMW write technique is used to post data and error checking blocks to disk when insufficient information reside in the lower level cache. A faster Full Write technique (also referred to as ...

Storage system having plural buses

A storage system to be connected to a large-scale computer includes a plurality of first logical units connected to a host device, a plurality of second logical units connected to a storage device, a plurality of cache memories, and a common bus wired between these logical units and memories. The plurality of first logical units, the plurality of second logical units, and the plurality of cache memories are all made in the form of modules. The modules are detachably mounted to the common bus disposed on a back plane. The storage device can be made up of a plurality of small-size storage units arranged in an array. Thus, the storage system realizes its scalability. Since the plurality of first logical units, the plurality of second logical units, and the plurality of cache memories are duplexed and the common bus is made in the form of 2 channels, the storage system can perform degrade operation. Since plurality of first logical units, the plurality of second logical units, and the plurality ...

METHODS FOR DETERMINING ALIAS OFFSET OF A CACHE MEMORY

A redundant array of independent disk (RAID) stack determines a first number of processor cycles to reload first data from a first memory address of a main memory into a processor of a data processing system. The RAID stack loads second data from a second memory address of the main memory into the processor, where the second memory address is configured to be an address offset from the first memory address. The RAID stack reloads the first data from the first memory address of the main memory and determines a second number of processor cycles to reload the first data from the first memory address of the main memory. An alias offset of a cache memory associated with the processor of the data processing system is determined based on the first number of processor cycles and the second number of processor cycle.

Scalable protection scheme for protecting destaged data units

A method for disk failure protection, the method may include calculating a first set of parity units by processing a first group of sets of data units that are cached in a cache memory of a storage system; calculating a second set of parity units by processing the first group of sets of data units; wherein the calculating of the second set of parity units is responsive to a first shift that was virtually introduced between each set of data units of the first group of sets of data units; and destaging the first group of sets of data units and the first and second sets of parity units to the first group of disks.

ОТСЛЕЖИВАНИЕ "ГРЯЗНЫХ" ОБЛАСТЕЙ ЭНЕРГОНЕЗАВИСИМЫХ НОСИТЕЛЕЙ

FIELD: computer equipment.SUBSTANCE: method of recording records unfinished in a storage set provided by at least one data storage device, the method comprising steps of, on which at least one data storage device generates an area descriptor separating the storage set stored on the data storage device into at least two regions according to the size of the region; when receiving a request to store a data set at a location in a storage set: identifying an area in the storage set containing the location of the data set; marking the region as "dirty" in the region descriptor and initiating storage of the data set at the location in the storage set; after storing the data set in the location in the storage set, the region is marked as "clean" in the region descriptor.EFFECT: technical result consists in correction of inconsistencies of data sets arising as a result of failure.13 cl, 11 dwg РОССИЙСКАЯ ФЕДЕРАЦИЯ (19) RU (11) (13) 2 728 816 C2 (51) МПК G06F 11/10 (2006.01) ФЕДЕРАЛЬНАЯ СЛУЖБА ПО ИНТЕЛЛЕКТУАЛЬНОЙ СОБСТВЕННОСТИ (12) ОПИСАНИЕ ИЗОБРЕТЕНИЯ К ПАТЕНТУ (52) СПК G06F 11/1076 (2020.02); G06F 2211/1035 (2020.02) (21)(22) Заявка: 2016138143, 10.10.2011 (24) Дата начала отсчета срока действия патента: Дата регистрации: (73) Патентообладатель(и): МАЙКРОСОФТ ТЕКНОЛОДЖИ ЛАЙСЕНСИНГ, ЭлЭлСи (US) 31.07.2020 12.09.2011 US 13/229,871 (62) Номер и дата подачи первоначальной заявки, из которой данная заявка выделена: 2014109361 10.10.2011 (43) Дата публикации заявки: 12.12.2018 Бюл. № 35 2 7 2 8 8 1 6 R U Адрес для переписки: 129090, Москва, ул. Б.Спасская, 25, строение 3, ООО "Юридическая фирма Городисский и Партнеры" (54) ОТСЛЕЖИВАНИЕ "ГРЯЗНЫХ" ОБЛАСТЕЙ ЭНЕРГОНЕЗАВИСИМЫХ НОСИТЕЛЕЙ (57) Реферат: Изобретение относится к вычислительной согласно размеру области; при приеме запроса технике. Технический результат заключается в на сохранение набора данных в местоположении исправлении несогласованностей наборов в наборе хранения: идентифицируют область в данных, ...

Patent RU2016138143A3

`”ВУ“” 2016138143°” АЗ Дата публикации: 04.03.2020 Форма № 18 ИЗПМ-2011 Федеральная служба по интеллектуальной собственности Федеральное государственное бюджетное учреждение 5 «Федеральный институт промышленной собственности» (ФИПС) ОТЧЕТ О ПОИСКЕ 1. . ИДЕНТИФИКАЦИЯ ЗАЯВКИ Регистрационный номер Дата подачи 2016138143/08(060428) 10.10.2011 Приоритет установлен по дате: [ ] подачи заявки [ ] поступления дополнительных материалов от к ранее поданной заявке № [Х] приоритета по первоначальной заявке № 2014109361 из которой данная заявка выделена [ ] подачи первоначальной заявки № из которой данная заявка выделена [ ] подачи ранее поданной заявки № [Х] подачи первой(ых) заявки(ок) в государстве-участнике Парижской конвенции (31) Номер первой(ых) заявки(ок) (32) Дата подачи первой(ых) заявки(ок) (33) Код страны 1. 13/229,871 12.09.2011 05 Название изобретения (полезной модели): [Х] - как заявлено; [ ] - уточненное (см. Примечания) ОТСЛЕЖИВАНИЕ "ГРЯЗНЫХ" ОБЛАСТЕЙ ЭНЕРГОНЕЗАВИСИМЫХ НОСИТЕЛЕЙ Заявитель: МАЙКРОСОФТ ТЕКНОЛОДЖИ ЛАЙСЕНСИНГ, ЭлЭлСи, 0$ 2. ЕДИНСТВО ИЗОБРЕТЕНИЯ [Х] соблюдено [ ] не соблюдено. Пояснения: см. Примечания 3. ФОРМУЛА ИЗОБРЕТЕНИЯ: [Х] приняты во внимание все пункты (см. п см. Примечания [ ] приняты во внимание следующие пункты: р [ ] принята во внимание измененная формула изобретения (см. Примечания) 4. КЛАССИФИКАЦИЯ ОБЪЕКТА ИЗОБРЕТЕНИЯ (ПОЛЕЗНОЙ МОДЕЛИ) (Указываются индексы МПК и индикатор текущей версии) С06Е 11/10 (2006.01) 5. ОБЛАСТЬ ПОИСКА 5.1 Проверенный минимум документации РСТ (указывается индексами МПК) С06Е 11/00-11/10,10/16,11/20, 12/00,12/16, 13/00 5.2 Другая проверенная документация в той мере, в какой она включена в поисковые подборки: 5.3 Электронные базы данных, использованные при поиске (название базы, и если, возможно, поисковые термины): СТРО, СМГРА, О\У/РТ, ЕАРАТГУ, Езрасепеф, ]-Р]а(Раь К-РЛОМ, КРК, РАТЕМТЗСОРЕ, Ра еагсв, КОРТО, ОЗРТО 6. ДОКУМЕНТЫ, ОТНОСЯЩИЕСЯ К ПРЕДМЕТУ ПОИСКА Кате- Наименование документа с указанием (где необходимо) ...

Safe write to multiply-redundant storage

NONVOLATILE MEDIA DIRTY REGION TRACKING

A storage set (e.g., an array of hard disk drives) may experience a failure, such as a loss of power, a software crash, or a disconnection of a storage device, while writes to the storage set are in progress. Recover from the failure may involve scanning the storage set to detect and correct inconsistencies (e.g., comparing mirrors of a data set or testing checksums). However, lacking information about the locations of pending writes to the storage set during the failure, this "cleaning" process may involve scanning the entire storage set, resulting in protracted recovery processes. Presented herein are techniques for tracking writes to the storage set by apportioning the storage set into regions of a region size (e.g., one gigabyte), and storing on the nonvolatile storage medium descriptors of "dirty" regions comprising in-progress writes. The post-failure recovery process may then be limited to the regions identified as dirty.

Safe write to multiply-redundant storage

An arrangement of apparatus for safely writing data and parity to multiply-redundant storage comprises a first storage component operable to store at least a first mark in a storage device to index uniquely a pattern to be written by at least a data write; a write component operable to perform the at least data write; a further storage component operable to overwrite a mark in the storage device with at least a further mark to index uniquely a pattern to be written by a parity write; and a further write component operable to perform the parity write. Preferably, the first storage component comprises a second storage component operable to overwrite said at least first mark in said storage device with a second mark to index a pattern to be written by a first parity write; and the write component is further operable to perform the first parity write.

Disk array device and method of updating error correction codes by collectively writing new error correction code at sequentially accessible locations

When new data for writing is sent from a host device, old data and old parities are read after a search time respectively, and a new parity is generated with the new data, the old data and the old parities, and the new parity is stored in a cache memory, and when the number of the new parities corresponding to a plurality of write data becomes more than a predetermined value set by a user or when there is a period of time in which no read request or no write request is issued, new parities are collectively written to a drive for storing parities. In this case, a plurality of new parities are written in a series of storing positions, where a plurality of old parities are stored, in a predetermined access order independent of the stored positions of corresponding old parities. At least to a plurality of storing positions in a track, these new parities are written in the order of positions in a track. To the storing positions which belong to a different track or to a different cylinder, new ...

Memory system and method of using same

A memory system and method of using same are provided. One embodiment of the system includes a semiconductor memory that is configured to include a multiplicity of memory segments. The memory segments are grouped into groups. Each of the groups includes N respective memory segments, where N is an integer number. In each respective group of memory segments, the N respective memory segments include respective data segments and a respective parity segment. Also in each respective group of memory segments, the respective parity segment in the respective group stores a respective data value P that may be calculated by a logical exclusive-or of respective data values stored in the respective data segments in the respective group.

Data replication method over a limited bandwidth network by mirroring parities

A method dramatically reduces the amount of data to be stored and transferred in a networked storage system. Preferably, the network storage system provides continued data protection through mirroring/replication, disk-to-disk backup, data archiving for future retrieval, and Information Lifecycle management (ILM). The idea is to leverage the parity computation that exists in RAID systems. By caching, transferring, and storing data parity or delta bytes of changes on a block as opposed to data block itself, substantial data reduction is possible without using sophisticated compression algorithms at the production side to minimize performance impacts upon production servers. Data can be computed using the parity/delta and previously existing data at mirror side, replication side, backup storage, or at retrieval time upon events such as failures or ILM operations.

Array type disk system updating redundant data asynchronously with data access

In a disk array system, data read out and data written anew are temporarily held as former data in a former data holding portion. When a write operation has occurred, a CPU searches the holding portion for write data, it generates update data from the new and former write data items, and it holds the generated update data in an update data holding portion. In addition, the CPU stores the storage address of redundant data associated with the held update data, as log data in a log data holding portion. Further, the CPU operates asynchronously with the write operation to read out the redundant data of the address of the holding portion, to calculate new redundant data from the read redundant data and the held update data, and to write the new redundant data into the address of the log data. On this occasion, a parity area and a data area are separated so as to heighten read/write processing speeds and a parity generation processing speed.

Implementing storage adapter performance optimization with parity update footprint mirroring

A method and controller for implementing storage adapter performance optimization with parity update footprint mirroring between dual adapters minimizing firmware operations, and a design structure on which the subject controller circuit resides are provided. Each of a first controller and a second controller includes a plurality of hardware engines, a control store configured to store parity update footprint (PUFP) data; a data store; and a nonvolatile random access memory (NVRAM). One controller operates in a first initiator mode for transferring PUFP data to the other controller operating in a target mode. Respective initiator hardware engines transfers PUFP data from the initiator control store, selectively updating PUFP data, and writing PUFP data to the initiator data store and to the initiator NVRAM, and simultaneously transmitting PUFP data to the other controller. Respective target hardware engines write PUFP data to the target data store and the target NVRAM, eliminating firmware ...

SYSTEM AND METHOD FOR MANAGING A NON-VOLATILE STORAGE RESOURCE AS A SHARED RESOURCE IN A DISTRIBUTED SYSTEM

A data storage system has a plurality of hosts that request writes of data to a relatively high-performance storage device (RHPSD) such as NVRAM, which may be one of a plurality of RHPSDs in a plurality of storage nodes. A storage management system receives the write requests and writes received data to the RHPSD. According to an allocation policy, the storage management system indicates to at least one of the hosts that it should limit its use of RHPSD and it then discards data upon indication from that host to do so. Before being discarded from the RHPSD, the data may be written to a persistent storage device. 1. A method for managing a shared storage resource in a data storage system , comprising:receiving, from at least one host of a plurality of hosts, requests to write data to a relatively high-performance storage device;in response to the requests, writing data to the relatively high-performance storage device;according to an allocation policy, indicating to a particular host, of the plurality of hosts, that it should limit its use of the relatively high-performance storage device; receiving, from the particular host, an indication of data to discard from the relatively high-performance storage device; and', 'discarding the data that corresponds to the indication from the relatively high-performance storage device;, 'after indicating to the particular host that it should limit its use of the relatively high-performance storage devicewherein receiving the indication of data to discard includes receiving a request by the particular host to delete a subset of the written data in the relatively high-performance storage device; andwherein discarding the data that corresponds to the indication includes discarding the subset of the written data in the relatively high-performance storage device.2. The method of claim 1 , further comprising dynamically allocating space in the relatively high-performance storage device to each host of the plurality of hosts.3. The ...

DATA REDUNDANCY METHODS AND APPARATUS

A data storage apparatus has a plurality of n disks and data comprising a plurality of n data groupings stored respectively across the plurality of n disks. Each one of the n data groupings comprise a data portion and a data redundancy portion. Advantageously, the n data portions are recoverable from any and all combinations of n-m data grouping(s) on n-m disk(s) when the other m data grouping(s) are unavailable, where 1 < m< n. Application of the coding is also applied to rf transmission and a redundant server configuration.

Storage apparatus and data storage method using the same

A storage apparatus (4) comprises a disk device (5) and a disk controller (6) for controlling the disk device. The disk controller provides a data volume including an actual volume and virtual volume with a volume capacity virtualization function. The virtual volume is associated with a pool volume for storing the actual data and the actual data is stored in the pool volume. In response to a write command from a host computer (3), the disk controller compresses write data under RAID 5 control and stores the compressed data in a storage area in the actual volume. If the entire compressed data cannot be stored in that storage area, the disk controller stores the remaining portion of the compressed data in the virtual volume.

System und Verfahren zur hierarchischen Datenspeicherung

STORING DATA ON STORAGE NODES

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for storing data on storage nodes. In one aspect, a method includes receiving a file to be stored across a plurality of storage nodes each including a 5 cache. The file is stored by storing portions of the file each on a different storage node. A first portion is written to a first storage node's cache until determining that the first storage node's cache is full. A different second storage node is selected in response to determining that the first storage node's cache is full. For each portion of the file, a location of the portion is recorded, the location indicating at least a storage node storing 10 the portion.

STORING DATA ON STORAGE NODES

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for storing data on storage nodes. In one aspect, a method includes receiving a file to be stored across a plurality of storage nodes each including a 5 cache. The file is stored by storing portions of the file each on a different storage node. A first portion is written to a first storage node's cache until determining that the first storage node's cache is full. A different second storage node is selected in response to determining that the first storage node's cache is full. For each portion of the file, a location of the portion is recorded, the location indicating at least a storage node storing 10 the portion.

METHOD AND APPARATUS FOR EFFICIENTLY DESTAGING SEQUENTIAL I/O STREAMS

A method for destaging write data from a storage controller to storage devices is provided. The method includes determining that a cache element should be transferred from a write cache of the storage controller to the storage devices, calculating that a dirty watermark is above a dirty watermark maximum value, identifying a first cache element to destage from the write cache to the storage devices, transferring a first data container including the first cache element to the storage devices, and incrementing an active destage count. The method also includes repeating determining, calculating, identifying, transferring, and incrementing if the active destage count is less than an active destage count maximum value. The active destage count is a current number of write requests issued to a virtual disk that have not yet been completed, and the virtual disk is a RAID group comprising one or more specific storage devices.

DEVICE AND METHOD FOR MANAGING DISK CACHE ON DISK ARRAY SYSTEM

PURPOSE: A device and a method for managing a disk cache on a disk array system are provided to constantly maintain or shorten a cache searching time, and to efficiently process the recovery or the expansion of a disk by applying a double tag of a stripe tag independently managing only a cache tag managing the data and the parity, and the cache tag included to the same stripe. CONSTITUTION: A hash table(100) has the intrinsic entry arrangement formed by a double pointer. The stripe tag is connected to each entry in the hash table(100), and independently manages the cache tag(102) included to the same stripe as the cache tag by each stripe. The stripe tag(104) connects the cache tags(102) to one stripe tag defined for the corresponding stripe with a double connection list. The stripe tag(104) comprises a front point region, a rear point region, a stripe number region, a strip lock state region, a cache tag number region, a cache tag pointer region, and a last cache tag pointer region. © ...

반도체 기억 장치 및 그 제어 방법

... 신뢰성을 높이고, 또한, 하나의 계층으로 SSD를 효율적으로 제어한다. 본 발명에 따른 반도체 기억 장치는, 프라이머리 메모리(3)와, 프라이머리 메모리(3)에 저장되는 데이터에 대응하는 데이터가 저장되는 미러 메모리(4)와, 버퍼 메모리(5) 중 적어도 하나의 메모리와, 적어도 하나의 메모리를 제어하여, 적어도 하나의 메모리에 데이터를 저장하고, 적어도 하나의 메모리로부터 데이터를 판독하는 제어 장치(2)를 구비한다.

MEMORY SYSTEM AND METHOD FOR USING SAME

PROBLEM TO BE SOLVED: To increase available memory resources in a memory system employing a fault tolerant technology. SOLUTION: The memory system includes a semiconductor memory configured to include a plurality of memory segments, wherein each of the memory segments is grouped into each group. Each group includes N memory segments, where N is an integer. In each respective group of the memory segments, the N respective memory segments comprise respective data segments and respective parity segments. Also in each respective group of memory segments, the respective parity segments in the respective groups stores respective data values P derived by a logical exclusive OR of respective data values which are stored in the respective data segments in the respective groups. COPYRIGHT: (C)2007,JPO&INPIT ...

ОТСЛЕЖИВАНИЕ " ГРЯЗНЫХ" ОБЛАСТЕЙ ЭНЕРГОНЕЗАВИСИМЫХ НОСИТЕЛЕЙ

1. Способ регистрации на компьютере, имеющем процессор, операций записи, незаконченных в наборе хранения, обеспеченном посредством, по меньшей мере, одного устройства хранения данных, причем упомянутый способ содержит этапы, на которых:выполняют на процессоре инструкции, сконфигурированные, чтобы:на по меньшей мере одном устройстве хранения данных формировать дескриптор областей, разделяющий набор хранения, сохраненный на устройстве хранения данных, на по меньшей мере две области согласно размеру области;при приеме набора данных, который должен быть сохранен в местоположении в наборе хранения:идентифицировать область в наборе хранения, содержащую местоположение набора данных;помечать область как "грязную" в дескрипторе областей; иинициировать сохранение набора данных в местоположении в наборе хранения;после сохранения набора данных в местоположении в наборе хранения, помечать область как "чистую" в дескрипторе областей.2. Способ по п. 1, при этом соответствующие "грязные" области идентифицируют соответствующие области в устройстве хранения данных согласно схеме обращения к областям, выбранной из набора схем обращения к областям, содержащего:схему физического обращения к области, идентифицирующую физическое местоположение области на устройстве хранения данныхнабора хранения; исхему логического обращения к области, идентифицирующую логическое местоположение области на логическом устройстве набора хранения.3. Способ по п. 1:при этом набор хранения содержит, по меньшей мере, два набора областей для областей; исоответствующие наборы областей содержат, по меньшей мере, один дескриптор областей, представ

ОТСЛЕЖИВАНИЕ "ГРЯЗНЫХ" ОБЛАСТЕЙ ЭНЕРГОНЕЗАВИСИМЫХ НОСИТЕЛЕЙ

Memory system and method of using same

Data management architecture

Storage apparatus and data integrity assurance method

A channel control unit of a storage apparatus is provided with: a variable-length DMA (Direct Memory Access) that performs data transfer of variable-length data sent to or received from the host computer in accordance with an I/O request; a fixed-length DMA that performs data transfer of fixed-length data to and from the cache memory; and a buffer intervening between the variable-length DMA and the fixed-length DMA. In performing the data transfer of the fixed-length data to the cache memory, the fixed-length DMA divides the variable-length data into multiple sets of the fixed-length data each having a data size equivalent to a unit size of data managed in the cache memory, and adds a first integrity code to the last fixed-length data set of the fixed-length data sets generated by the division, the first integrity code being generated based on the entire variable-length data.

RAID-5 disk having cache memory implemented using non-volatile RAM

A computer implemented cache memory for a RAID-5 configured disk storage system to achieve a significant enhancement of the data access and write speed of the raid disk. A memory cache is provided between the RAID-5 controller and the RAID-5 disks to speed up RAID-5 system volume accesses. It utilizes the time and spatial locality property of parity blocks. The memory cache is central in its physical architecture for easy management, better utilization, and easy application to a generalized computer system. The cache blocks are indexed by their physical disk identifier to improve the cache hit ratio and cache utilization.

Method and system for rebuilding log-structured arrays

A method for rebuilding contents of a malfunctioned direct access storage device within a log-structured array is disclosed. In accordance with the method and system of the present invention, each direct access storage device within a log-structured array is divided into multiple segment-columns, and each corresponding segment-column from each direct access storage device within the log-structured array forms a segment. A segment is first located within the direct access storage devices. A determination is made as to whether or not the segment is empty. In response to a determination that the segment is empty, a pointer is moved within a segment-column mapping table from pointing to a segment-column in the malfunctioned direct access storage device to point to a segment-column in a spare direct access storage device of the segment. In response to a determination that the segment is not empty, rebuilding contents of the segment-column in the malfunctioned direct access storage device to ...

Method and system for rebuilding log-structured arrays

A method for rebuilding contents of a malfunctioned direct access storage device within a log-structured array is disclosed. In accordance with the method and system of the present invention, each direct access storage device within a log-structured array is divided into multiple segment-columns, and each corresponding segment-column from each direct access storage device within the log-structured array forms a segment. A segment is first located within the direct access storage devices. A determination is made as to whether or not the segment is empty. In response to a determination that the segment is empty, a pointer is moved within a segment-column mapping table from pointing to a segment-column in the malfunctioned direct access storage device to point to a segment-column in a spare direct access storage device of the segment. In response to a determination that the segment is not empty, rebuilding contents of the segment-column in the malfunctioned direct access storage device to ...

Storing data on storage nodes

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for storing data on storage nodes. In one aspect, a method includes receiving a file to be stored across a plurality of storage nodes each including a cache. The file is stored by storing portions of the file each on a different storage node. A first portion is written to a first storage node's cache until determining that the first storage node's cache is full. A different second storage node is selected in response to determining that the first storage node's cache is full. For each portion of the file, a location of the portion is recorded, the location indicating at least a storage node storing the portion.

System and method for processing write-in in HDD using 4K block size

在使用大的块尺寸(例如4KB)来存储数据并响应于来自使用小的块尺寸(例如512字节)的客户端的读和写请求的磁盘驱动器中，至少被读取数据的起始和结尾4K块被高速缓冲存储。因为作为写请求的对象的大量磁盘数据首先被读取，在随后的写请求上，驱动器控制器确定起始和结尾块是否在高速缓冲存储器中，如果在，将新数据写到那些块上，为它们计算完整的ECC，然后为插入的块计算ECC并将新数据写入到插入的块中。如果起始和结尾块两者都不在高速缓冲存储器中，驱动器控制器执行由用户选择的高数据完整性例程和高性能例程。

CONTROLLER AND DATA RECORD METHOD OF RAID

PURPOSE: A RAID(Redundant Arrays of Inexpensive Disks) controller and a data record method, are provided to improve the function of a RAID subsystem, when it distinguishes a dirty block included in a cache memory that needs posting to a disk device due to a record operation. CONSTITUTION: A disk block(310) has a label for representing a logical block number of a dirty block which exists in a low-level cache. A plurality of blocks(2-8,10-30) of a stripe'0' exist in the low-level cache. Also, blocks(80-120) of a stripe'1', blocks(128-170) of a stripe'2', blocks(200-0210) of a stripe'3', blocks(225-240) of a stripe'4' and blocks(320-383) of a stripe'5' exist in the low-level cache. A stripe management data structure(300) exist in a high-level cache. A stripe(200) is illustrated as a label on the stripe management data structure(300). COPYRIGHT 2001 KIPO ...

Disk array system based on disks with a fixed-length unit of access

Conventional methods for appending a validation code are not applicable to a disk array system in which the disk array comprises disk devices having a fixed sector length. The present invention solves this problem by separating validation codes from data blocks, bundling them together in blocks that can be easily matched with sectors, and carrying out all the associated management and control by hardware, such as coordination between validation codes and data blocks and operations of reading from and writing into the disk devices, thereby offering the same level of reliability as with conventional systems.

METHOD AND APPARATUS FOR WRITING DATA TO A DISK ARRAY

A method for writing data to a RAID 5 configuration of hard disks writes two or more items of data to a data stripe together. The method includes the determining of the suitability of data items to be written together, the storing of the new data items to temporary buffers, the reading of the original data and parity from the hard disk to the temporary buffers, the modification of the parity and the writing of the new data and new parity to the hard disks.

Disc array system having disc storage devices dispersed on plural boards and accessible at withdrawal of part of the boards

A disc array system has a plurality of disc storage devices (i.e., drives) constituting a parity group and mounted in a distributed manner on different boards. Where any one drive in the same parity group develops a fault, the board carrying the faulty drive is withdrawn from the mother board for repair. If the CPU issues a write request for data held in the faulty drive or in any normal data on the same board, the requested data is recovered from the multiple data retained in the other drives constituting the same logical group and mounted on the other boards. The recovered data is sent to the CPU. If the CPU supplies write data to the faulty drive or to any normal drive on the same board, the supplied write data is held temporarily in a cache memory in an array controller. Later, when the board is repaired and replaced onto the mother board, the data to be held in the alternate drive having replaced the faulty drive is recovered from the data in the other drives, and the recovered data ...

Storage sub-system having expanded data read

A storage sub-system employs a staging control information table by which staging of data to be read and redundant data thereof can be executed together to reduce response time in the event of a data read failure. The staging control information table also permits pre-read staging to be executed in the forward, backward or both the forward and backward directions, to reduce response time.

Data storage with a distributed virtual array

A data storage system includes a plurality of hosts, each of which includes at least one processor and communicates over a network with a plurality of storage nodes, at least one of which has at least one storage device, at least one storage controller, and at least one non-volatile memory. At least one process within a host issues data storage read/write requests. At least one of the hosts has a cache for caching data stored in at least one of the storage nodes. The host writes data corresponding to a write request to at least one remote non-volatile memory and carries out at least one storage processing function; data in the written-to node may then be made available for subsequent reading by a different one of the hosts. Examples of the storage processing function include compression, ECC computation, deduplicating, garbage collection, write logging, reconstruction, rebalancing, and scrubbing.

System and method for identifying inconsistent parity in an array of storage

A system and method are provided that is used by software implemented Redundancy Array of Inexpensive Disk (RAID) arrays to achieve adequate performance and reliability, as well as to improve performance or low cost hardware Raids. The enhancements to the basic RAID implementation speeds up recovery time for software RAIDS. A method is provided for storing data in an array of storage devices. A plurality of block locations on the storage devices are logically arranged as a parity group wherein a parity block stored in a block location as part of a parity group is logically derived from the combination of data blocks stored in the parity group, and each block in a parity group is stored on a different storage device. A plurality of parity groups are grouped into a parity group set. A request is received to write a new data block location on a storage device. The old data block stored at the block location is read. The new data block is written to the block location. When the parity set is ...

PARITY CACHE FOR RAID RELIABILITY, ACCESSIBILITY, AND SERVICEABILITY OF A MEMORY DEVICE

There are provided methods and systems for improving RAS features of a memory device. For example, there is provided a system that includes a memory and a memory side cache. The system further includes a processor that is configured to minimize accesses to the memory by executing certain operations. The operations can include computing a new parity based on old data, new data, and an old parity in response to data from the memory side cache being written to the memory.

System zur Kontrolle der Befehlswarteschlange der Paritätsplatte in einer Speicherplattenanordnung

System and method for hierarchical data storage

Writing data cross storage devices in an erasure-coded system

A redundant array of independent discs has a one or more controllers 20 connected to one or more placement nodes 40. The controllers generate parity blocks for the data blocks written to the array. The placement nodes determine the locations in the array, at which the data and parity blocks to be written. The data is then written to the storage devices 50. The coding scheme used to generate the parity blocks may be used to select where to write the blocks. The locations are stored in placement metadata 30 accessible to the placement nodes. When reading or updating the blocks, the placement nodes use the metadata to retrieve the blocks.

Storage controller, and storage device failure detection method

Even when a failure incapable of being detected by a single guarantee code occurs in data, a storage controller of the present invention can detect and restore this failure. The controller, upon receiving a write command from a host, establish a first data guarantee code in the write data, and establish a second data guarantee code in the parity related to the write data. Upon receiving a read command from the host, the controller determines the correctness of the data based on the first data guarantee code, and also detects the presence or absence of a failure by comparing the first data guarantee code with the second data guarantee code. When a failure is detected, the controller restores the failure on the basis of RAID technology.

SYSTEM FOR OPTIMIZING THE PERFORMANCE AND RELIABILITY OF A STORAGE CONTROLLER CACHE OFFLOAD CIRCUIT

ディスクアレイ制御装置、ディスクアレイ装置、及び、ディスクアレイ制御方法

Systeme und Verfahren zur internen Datenkompression in Plattenlaufwerken

Die vorliegende Erfindung bezieht sich auf Systeme und Verfahren zur Datenspeicherungskomprimierung.

System and method for hierarchical data storage

A system and method for storing data, the system having one or more storage devices, caches data from a sender into a first random-access structure located in a first cache level, caches data from the first cache level into a log structure located in a second cache level, and stores data from CL into a second random-access structure located in a storage level, wherein CL is the first cache level or the second cache level. In further embodiments of the invention, the second cache level caches in the log structure parity data for the data cached in the log structure. In a still further embodiment of the invention, the storage level stores in the second random-access structure parity data for the data stored in the second random-access structure.

Nonvolatile media dirty region tracking

A storage set (e.g., an array of hard disk drives) may experience a failure, such as a loss of power, a software crash, or a disconnection of a storage device, while writes to the storage set are in progress. Recover from the failure may involve scanning the storage set to detect and correct inconsistencies (e.g., comparing mirrors of a data set or testing checksums). However, lacking information about the locations of pending writes to the storage set during the failure, this "cleaning" process may involve scanning the entire storage set, resulting in protracted recovery processes. Presented herein are techniques for tracking writes to the storage set by apportioning the storage set into regions of a region size (e.g., one gigabyte), and storing on the nonvolatile storage medium descriptors of "dirty" regions comprising in-progress writes. The post-failure recovery process may then be limited to the regions identified as dirty.

NONVOLATILE MEDIA DIRTY REGION TRACKING

A storage set (e.g., an array of hard disk drives) may experience a failure, such as a loss of power, a software crash, or a disconnection of a storage device, while writes to the storage set are in progress. Recover from the failure may involve scanning the storage set to detect and correct inconsistencies (e.g., comparing mirrors of a data set or testing checksums). However, lacking information about the locations of pending writes to the storage set during the failure, this "cleaning" process may involve scanning the entire storage set, resulting in protracted recovery processes. Presented herein are techniques for tracking writes to the storage set by apportioning the storage set into regions of a region size (e.g., one gigabyte), and storing on the nonvolatile storage medium descriptors of "dirty" regions comprising in-progress writes. The post-failure recovery process may then be limited to the regions identified as dirty.

For cross-storage device of the data writing method and system

SYSTEM AND METHOD FOR COMMAND QUEUING ON RAID LEVELS 4 AND 5 PARITY DRIVES

METHOD AND APPARATUS TO PERFORM REDUNDANT ARRAY OF INDEPENDENT DISKS (RAID) OPERATIONS

Write back method for RAID apparatus

A RAID control apparatus comprises at least a cache memory; an update information management table for storing update information; an update information storage unit for storing, in the update information management table, update information by detecting a data update; a reference value generation unit for generating a reference value expressing a load of a write back processing by using a Small Write method and a Read & Bandwidth Write method based on the update information; a write method determination unit for determining a write method according to the reference value and a write unit for carrying out a write processing, in order to provide a write back method for a RAID apparatus capable of improving a processing speed at the time of updating even in the case of including the processing of updating a part of data stripes.

Storage unit and storage unit subsystem

An intermediate value derived from old and new data record values or old and new data themselves are sent from a control unit to a disk unit which stores a parity record as information necessary for updating parity. The disk unit reads an old parity record and generates a new value of parity record based on the read old parity and the information received from the control unit. The generated new value is stored in an empty record on the storage medium to which a read/write head is first positioned after the generation of the new value and in which effective data has not been stored. In a disk array system, a time required to update the parity record due to the updating of the data record is reduced and a performance of the storage unit subsystem is improved.

Write journaling using battery backed cache

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.

Method and apparatus for increasing RAID write performance by maintaining a full track write counter

A method and apparatus for improving write performance in a disk array, wherein unnecessary track grouping is avoided during writes, by using a full track write counter. When a write request is received, the full track write counter for tracks in a stripe of tracks associated with the write request is analyzed to determine whether the write request involves a full track write. A cache destage is subsequently executed based on the analysis. When the write to cache is a full track write, a previous track full track count is fetched from a previous track's full write counter, a full track count of the tracks associated with the write request are set to be equal to the minimum of either the stripe width or the previous track's full track count plus one. When the full track write counter of the last track in the stripe is equal to the stripe width, each track in the stripe is processed for destage, new parity for the stripe is generated based on modifications to each track and new data resulting ...

Method and apparatus to perform redundant array of independent disks (RAID) operations

A method and apparatus to compute a Q syndrome for RAID 6 through the use of AES operations is provided. In an embodiment, the result of GF multiplication performed using the AES operations allows RAID-6 support to be provided without the need for a dedicated RAID controller.

High-performance log-structured RAID

This invention describes a high-performance, log-structured implementation of a RAID subsystem that can be efficiently implemented in software. The methods described here allow the RAID subsystem to achieve high performance without using specialized hardware such as non-volatile memory or hardware XOR/DMA engines. Furthermore, the RAID implementation described here is well suited for supporting many functions required for advanced storage virtualization such as virtual disks, graceful addition and removal of disks, tolerating multi-disk failures, and snapshots.

METHOD AND APPARATUS FOR READING AND WRITING DATA IN FILE SYSTEM

Embodiments of the present invention disclose a method and an apparatus for reading and writing data in a file system, which are applicable to the field of communications technologies. In the embodiments of the present invention, the file system supports file-level redundancy algorithm operations of independent disks; after receiving a file read/write request, the file system determines read/write locations of the data to be read/written in the data strip, sequentially caches the to-be-read/written data information corresponding to at least one data strip, and processes the cached data information of at least one data strip. In this way, after the to-be-read/written data information corresponding to a complete data strip is cached, the data is read/written by using a data strip as a unit, and it is not necessary to write the file read/write request into the LUN virtual block device first and then use the RAID module to access the hard disk drive whenever the file read/write request is received, thereby improving efficiency of reading/writing data.

Redundant array of independent disks with deferred parity-block updates

There is provided a method and apparatus for effectuating data updates on a fault-tolerant storage device having a plurality of disk-drive units (18, 20, 22, 24, 26) forming a disk array (16), with parity-block updates temporarily suspended to provide increased performance. Parity-block updates are typically deferred until the array (16) is idle, thereby relaxing the coherency between data and parity for short periods of time. In this fashion, data is written onto the array (16) with no parity error correction information being present for a short amount of time, which decreases the rotational latency of the drive units (18, 20, 22, 24, 26) visible to external requests. Data updates are effectuated by identifying the blocks (30, 32, 34, 36, 38) in the array (16) where data is to be written, i.e. target areas of a stripe. New data is then written directly to the target areas without reading the old data present therein. A "needs parity rebuild bit" (NPRB) is written to non-volatile memory ...

Data redundancy methods and apparatus

Caching techniques for improving system performance in raid applications

PARITY CALCULATION FOR RAID WRITE CACHE

A method for using parity (28) and a write cache (30) for a RAID (12, 14) by adding a check code (50) for the parity data (34) itself. In addition, the time during which the parity check code (50) is unprotected is reduced by using a single loop to calculate the old parity code (72) and verify it, determine the new parity information (74) itself from the new write data, and calculate the new parity check code (76). Rather than cycle through all the parity blocks to calculate the old check code, and verify that it matches what is stored, the old check code is reconstructed block-by-block as the new parity is generated for each block in a loop. In addition, the new parity check code is constructed bit-by-bit at the same time.

PARITY CALCULATION FOR RAID WRITE CACHE

A method for using parity (28) and a write cache (30) for a RAID (12, 14) by adding a check code (50) for the parity data (34) itself. In addition, the time during whic h the parity check code (50) is unprotected is reduced by using a single loop to calculate the old parity code (72) and verify it, determine the new parity information (74) itself from the new write data, an d calculate the new parity check code (76). Rather than cycle through all the parity blocks to calculat e the old check code, and verify that it matches what is stored, the old check code is reconstructed block-by-block as the new parity is generated for each block in a loop. In addition, the new parity check code is constructed bit-by-bit at the same time.

MEMORY DEVICE SYSTEM FOR IMPROVING DATA INPUT/OUT PERFORMANCE AND METHOD OF EMBODYING DATA RESTORATION INFORMATION CACHE THEREBY

PURPOSE: A memory device system for improving data input/output performance and a method of embodying a data restoration information cache thereby are provided to reduce the overhead of data restoration information read operation in order to enhance data input/output performance. CONSTITUTION: A RAID(Redundant Arrays of Inexpensive Disks) system is composed of a CPU(30), a controller(34), drives(39) and caches(38). The CPU(30) controls the RAID system overall. The controller(34) under the control of the CPU(30) dispersedly stores data transmitted from a host computer to each drive array(39) or regenerates data written in each drive array(39). The drives(39) connected to the controller(34) stores and regenerates the data transmitted from a host computer and data restoration information, or parity information, under the control of the controller(34). The caches(38) connected to each input/output bus(36) between the controller(34) and each drive(39) stores parity information. COPYRIGHT 2001 ...

REBUILD OF REDUNDANT SECONDARY STORAGE CACHE

Rebuild of redundant secondary storage cache

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.

STORING DATA ON STORAGE NODES

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for storing data on storage nodes. In one aspect, a method includes receiving a file to be stored across a plurality of storage nodes each including a cache. The file is stored by storing portions of the file each on a different storage node. A first portion is written to a first storage node's cache until determining that the first storage node's cache is full. A different second storage node is selected in response to determining that the first storage node's cache is full. For each portion of the file, a location of the portion is recorded, the location indicating at least a storage node storing the portion.

Method and apparatus for operating an array of storage devices

A storage controller operates an array of parity protected data storage units as a RAID level 5. One of the storage units is a dedicated write assist unit. The assist unit is a temporary storage area for data to be written to the other units. When the array controller receives data from a host, it first writes the data to the assist unit. Because the assist unit is not parity protected and is only temporary storage, it is possible to write data to the assist unit sequentially, without first reading the data, greatly reducing response time. The array controller signals the CPU that the data has been written to storage as soon as it has been written to the assist unit. Parity in the array is updated asynchronously. In the event of system or storage unit failure, data can be recovered using the remaining storage units and/or the assist unit. The write assist unit also doubles as a spare unit. Data recovered from a failed unit can be stored on the write assist, which then ceases to function ...

System, apparatus and method for multi-level cache in a multi-processor/multi-controller environment

This inventive provides a multiple level cache structure and multiple level caching method that distributes I/O processing loads including caching operations between processors to provide higher performance I/O processing, especially in a server environment. A method of achieving optimal data throughput by taking full advantage of multiple processing resources is disclosed. A method for managing the allocation of the data caches to optimize the host access time and parity generation is disclosed. A cache allocation for RAID stripes guaranteed to provide fast access times for the XOR engine by ensuring that all cache lines are allocated from the same cache level is disclosed. Allocation of cache lines for RAID levels which do not require parity generation and are allocated in such manner as to maximize utilization of the memory bandwidth is disclosed. Parity generation which is optimized for use of the processor least utilized at the time the cache lines are allocated, thereby providing ...

Parity-based raid system configured to protect against data corruption caused by the occurrence of write holes

A RAID system is provided in which the RAID controller of the system causes a predetermined number, N, of IO commands to be queued in a memory element, where N is a positive integer. After the N IO commands have been queued, the RAID controller writes N locks associated with the N IO commands in parallel to a service memory device. The RAID controller then writes N stripes of data and parity bits associated with the N IO commands to the PDs of the system to perform striping and parity distribution. If a catastrophic event, such as a power failure, occurs, the RAID controller reads the locks from the service memory device and causes parity to be reconstructed for the stripes associated with the locks. These features improve write performance while preventing the occurrence of data corruption caused by write holes.

Speichergerät und Verfahren zu seiner Steuerung

Memory system and method of using same

METHOD OF IMPROVING INPUT/OUTPUT PERFORMANCE OF A RAID SYSTEM USING A MATRIX STRIPE CACHE FOR REDUCING THE NUMBER OF INPUTS AND OUTPUTS TO IMPROVE READ AND WRIGHT PERFORMANCES

PURPOSE: A method for improving input/output performance of an RAID(Redundant Array of Independent Disks) system using an MSC(Matrix Stripe Cache) is provided to instruct disks to perform read and write operations based on an rxw matrix to which additional read and write operations are added to reduce the number of read and write inputs and output, thereby improving write performance. CONSTITUTION: A method for improving input/output performance of an RAID system using an MSC includes a first step of generating an rxw matrix corresponding to a read/write matrix before row combination from a unit MSC which performs a write operation on a disk, a second step of generating a row-combined rxw matrix corresponding to a final read/write matrix through row combination from the rxw matrix generated in the first step, and a third step of performing a read operation based on the row-combined rxw matrix, carrying out an XOR operation on each row of the row-combined rxw matrix, and performing a write ...

DATA REDUNDANCY METHODS AND APPARATUS

A data storage apparatus has a plurality of n disks and data comprising a plurality of n data groupings stored respectively across the plurality of n disks. Each one of the n data groupings comprise a data portion and a data redundancy portion. Advantageously, the n data portions are recoverable from any and all combinations of n-m data grouping(s) on n-m disk(s) when the other m data grouping(s) are unavailable, where 1 < m< n. Application of the coding is also applied to rf transmission and a redundant server configuration.

System and method for maintaining a data redundancy scheme in a solid state memory in the event of a power loss

Embodiments of the invention are directed to systems and methods for reducing an amount of backup power needed to provide power fail safe preservation of a data redundancy scheme such as RAID that is implemented in solid state storage devices where new write data is accumulated and written along with parity data. Because new write data cannot be guaranteed to arrive in integer multiples of stripe size, a full stripe's worth of new write data may not exist when power is lost. Various embodiments use truncated RAID stripes (fewer storage elements per stripe) to save cached write data when a power failure occurs. This approach allows the system to maintain RAID parity data protection in a power fail cache flush case even though a full stripe of write data may not exist, thereby reducing the amount of backup power needed to maintain parity protection in the event of power loss.

Disk array apparatus and control method thereof

Proposed are a disk array apparatus and a control method thereof which facilitate data processing such as write processing and read processing even if the block sizes handled by a host computer are different. If a first write command is received from the host computer, the controller of the disk array apparatus divides first write data into a plurality of second write data, and adds a first guarantee code and writes this data to the plurality of first storage devices; if a first read command is received from the host computer, the controller reads a plurality of first read data from the plurality of first storage devices, generates second read data which is obtained by combining [the plurality of first read data], and adds a second guarantee code [to the second read data] and transmits this data to the host computer; if a second write command is received from the host computer, the controller generates fourth write data based on third write data, adds a third guarantee code [to the fourth write data] and writes this data to the plurality of second storage devices and, if the second read command is received from the host computer, the controller reads third read data from the plurality of second storage devices, divides this data into fourth read data, and adds a fourth guarantee code and transmits the data to the host computer

Error detection within a memory

Embodiments of systems and methods for detecting errors that occur in association with an access to a memory and providing an associated error status are presented herein. According to one embodiment, an access to a memory may be received, where the access comprises a request tag. A request parity is determined based on the request tag and a stored tag and a stored parity associated with the request tag are also determined. An error correction status is determined based on the stored tag and the stored parity associated with the request tag. Additionally, a parity hotness is determined by comparing the request parity and the stored parity and a tag hotness is determined by comparing the request tag and the stored tag. An error status associated with the access is determined based on the parity hotness, the tag hotness and the error correction status.

Storage system, control method thereof, and program

A RAID control unit forms a redundant configuration of RAID with respect to a physical device including a plurality of disk devices. A cache control unit processes data in page units corresponding to a stripe of the disk devices. A cache area placement unit, when it receives a write request from an upper-level device, places, in a cache memory, a cache area which is provided with a plurality of page areas and has the same size as the stripe area. When new data in the cache memory which is newer than the data in the physical device is to be written back to the storage device, a write-back processing unit generates new parity data by use of an unused area in the cache stripe area, and then writes the new data and the new parity to the corresponding storage devices.

Storage Controller and Method for Managing Modified Data Flush Operations From a Cache

A storage controller maintaining a cache manages modified data flush operations. A set-associative map or relationship between individual cache lines in the cache and a corresponding portion of the host managed or source data store is generated in such a way that a quotient can be used to identify modified data in the cache in the order of the source data's logical block addresses. The storage controller uses a collision bitmap, a dirty bit map and a flush table when flushing data from the cache. The storage controller selects a quotient and identifies modified cache lines in the cache identified by the quotient. As long as the quotient remains the same, the storage controller flushes or transfers the modified cache lines to the data store. Otherwise, when the quotient is not the same, the data in the cache is skipped. A linked list is used to traverse skipped cache lines.

DYNAMIC MANAGEMENT OF EXPANDABLE CACHE STORAGE FOR MULTIPLE NETWORK SHARES CONFIGURED IN A FILE SERVER

Expandable cache management dynamically manages cache storage for multiple network shares configured in a file server. Once a file is written to a directory or folder on a specially designated network share, such as one that is configured for “infinite backup,” an intermediary pre-backup copy of the file is created in an expandable cache in the file server that hosts the network share. On write operations, cache storage space can be dynamically expanded or freed up by pruning previously backed up data. This advantageously creates flexible storage caches in the file server for each network share, each cache managed independently of other like caches for other network shares on the same file server. On read operations, intermediary file storage in the expandable cache gives client computing devices speedy access to data targeted for backup, which is generally quicker than restoring files from backed up secondary copies. 1. A system for retrieving data from a network share cache if available instead of retrieving the data from a secondary copy , the system comprising:a file server in communication with a first client computing device, wherein the file server comprises a plurality of storage volumes;a secondary storage device in communication with the file server; receiving from a client computing device a read request in reference to a first file, wherein the read request designates a first network share configured in the file server as a source for the read request,', 'based on the designated first network share in the read request, directing the read request to a first cache manager that is associated with the first network share, wherein the first cache manager executes on the file server,', 'if the first cache manager determines that the read request can be served at least in part from a first set of storage volumes configured in the file server that are associated with the first network share, retrieving, by the first cache manager, at least some of the data ...

ZONE AWARE REQUEST SCHEDULING AND DATA PLACEMENT

A method begins with receiving an encoded data slice that has associated therewith a slice name that is representative of a dispersed storage network (DSN) logical address. The method continues with accessing a DSN address to memory device mapping based on the DSN logical address to identify a memory device of the storage unit. The method continues with retrieving a logical zone to physical address space mapping of the identified memory device. The method continues with determining information regarding the encoded data slice and a logical zone of the memory device from the logical zone to physical address space mapping based on the encoded data slice information. The method continues with generating a physical address within the identified logical zone for storing the encoded data slice. The method continues with storing the encoded data slice within the identified memory device at the physical address. 1. A method comprises:receiving, by a storage unit of a disperse storage network (DSN), an encoded data slice for storage, wherein the encoded data slice has associated therewith a slice name that is representative of a DSN logical address, and wherein a data segment is dispersed storage error encoded to produce a set of encoded data slices, wherein the set of encoded data slices includes the encoded data slice;accessing, by the storage unit, a DSN address to memory device mapping based on the DSN logical address to identify one of a plurality of memory devices of the storage unit to produce an identified memory device;retrieving, by the storage unit, a logical zone to physical address space mapping of the identified memory device;determining, by the storage unit, information regarding the encoded data slice;determining, by the storage unit, a logical zone of the memory device from the logical zone to physical address space mapping based on the encoded data slice information to produce an identified logical zone;generating, by the storage unit, a physical address ...

Methods and Systems for Using a Write Cache in a Storage System

Methods and systems for storing data at a storage device of a storage system are provided. The data is first temporarily stored at a first write cache and an input/output request for a persistence storage device used as a second write cache is generated, when an I/O request size including the received data has reached a threshold value. The data from the first cache is transferred to the persistence storage device and a recovery control block with a location of the data stored at the persistence storage device is updated. An entry is added to a linked list that is used to track valid data stored at the persistence storage device and then the data is transferred from the persistence storage device to the storage device of the storage system. 1. A method , comprising:storing, temporarily by a storage server, received data in a first write cache;transferring, by the storage server, the received data from the first write cache to a second write cache, wherein the second write cache comprises nonvolatile storage and the first write cache volatile storage;updating, by the storage server, a recovery control block with a location of the received data stored in the second write cache and an entry in a tracking structure used to track valid data stored at the second write cache; andpersisting, by the storage server in response to a system failure, the recovery control block to a persistent storage device.2. The method of claim 1 , further comprising:re-building, by the storage server after power recovery, the tracking structure with the recovery control block;transferring, by the storage server, the received data from the second write cache to the first write cache based on the re-built tracking structure; andflushing, by the storage server after transfer to the first write cache, the received data from the first write cache to the persistent storage device.3. The method of claim 1 , further comprising:transferring, by the storage server, the received data from the second ...

DATA STORAGE WITH A DISTRIBUTED VIRTUAL ARRAY

A data storage system includes a plurality of hosts, each of which includes at least one processor and communicates over a network with a plurality of storage nodes, at least one of which has at least one storage device, at least one storage controller, and at least one non-volatile memory. At least one process within a host issues data storage read/write requests. At least one of the hosts has a cache for caching data stored in at least one of the plurality of storage nodes. The host writes data corresponding to a write request to at least one remote non-volatile memory and carries out at least one storage processing function; data in the written-to node may then be made available for subsequent reading by a different one of the hosts. Examples of the storage processing function include compression, ECC computation, deduplicating, garbage collection, write logging, reconstruction, rebalancing, and scrubbing. 1. A data storage system comprising:a plurality of host servers, each of which includes at least one processor;wherein the plurality of host servers includes a particular host server;wherein the particular host server communicates with a plurality of storage nodes over at least one network, a first storage node with at least one persistent storage device; and', 'a second storage node with a non-volatile memory;', 'wherein the at least one persistent storage device has higher latency than the non-volatile memory;', is executing at least one process that issues data storage read/write requests;', including:', 'writing the data, in a first write operation from the particular host server to the non-volatile memory within the second storage node without involving any persistent storage devices of the plurality of storage nodes, and', 'writing the data, in a second write operation from the particular host server to at least one persistent storage device of at least one storage node of the plurality of storage nodes, without involving the non-volatile memory within ...

Rebuild of redundant secondary storage cache

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.

DISTRIBUTED DATA METHOD FOR ENCRYPTING DATA

Techniques for performing data encryption on data to be stored within a storage system are provided. A client application executing on a host machine may generate a data storage write request to write data to a storage system. A host-side module, executing on the host machine receives the write request. The host-side module is configured to generate one or more fingerprints for the data corresponding to the write request, where the one or more fingerprints are unique identifiers used to identify data blocks that make up the data. The host-side module generates encrypted data by encrypting the data blocks using an encryption technique. The encrypted data is then sent to a storage node within the storage system. Deduplication may be performed on the encrypted data using the one or more generated fingerprints. 1. A method for packaging encrypted data in a storage system comprising:receiving, by a host-side module executing on a host machine, a data storage write request for particular data to be written, wherein the particular data has been encrypted and has one or more associated fingerprints based on an unencrypted version of the particular data;packaging, by the host-side module, the particular data into one or more clumps;generating, by the host-side module, one or more clump fingerprints based on the one or more associated fingerprints; andsending the one or more clumps to a storage node; andin response to a request for data that resides in a particular clump of the one or more clumps, locating the particular clump based, at least in part, on the one or more clump fingerprints.2. The method of claim 1 , wherein the particular data that has been encrypted comprises metadata containing an encryption key index value claim 1 , wherein the encryption key index value represents an identifier used to identify an associated encryption key from an encryption table maintained by the storage system.3. The method of claim 2 , further comprising:receiving, at the host-side ...

SCALABLE PROTECTION SCHEME FOR PROTECTING DESTAGED DATA UNITS

A method for disk failure protection, the method may include calculating a first set of parity units by processing a first group of sets of data units that are cached in a cache memory of a storage system; calculating a second set of parity units by processing the first group of sets of data units; wherein the calculating of the second set of parity units is responsive to a first shift that was virtually introduced between each set of data units of the first group of sets of data units; and destaging the first group of sets of data units and the first and second sets of parity units to the first group of disks. 1. A method for disk failure protection , the method comprises: 'wherein the first set of parity units facilitates a reconstruction of the first group of sets of data units when a first number of disks out of a first group of disks fail;', 'calculating a first set of parity units by processing a first group of sets of data units that are cached in a cache memory of a storage system;'} wherein a combination of the first and second sets of parity units facilitate a reconstruction of the first group of sets of data units when a second number of disks of the first group of disks fail;', 'wherein the second number is bigger than the first number; and, 'calculating a second set of parity units by processing the first group of sets of data units; wherein the calculating of the second set of parity units is responsive to a first shift that was virtually introduced between each set of data units of the first group of sets of data units;'}destaging the first group of sets of data units and the first and second sets of parity units to the first group of disks.2. The method according to wherein each set of data units comprises multiple (N) data units;wherein the first group of sets of data units comprises multiple (M) sets of data units;wherein the first shift equals at least one (S1) data unit;wherein the first set of parity units comprises N parity units; andwherein ...

High availability cache in server cluster

For a high availability cache, a cache module obtains permission to manage the cache in response to a failover event in a server cluster by communicating a cache coherency token. An update module rebuilds a cache directory from data stored in the cache and accesses the cache without reloading the data stored in the cache.

Data storage with a distributed virtual array

A data storage system includes a plurality of hosts, each of which includes at least one processor and communicates over a network with a plurality of storage nodes, at least one of which has at least one storage device, at least one storage controller, and at least one non-volatile memory. At least one process within a host issues data storage read/write requests. At least one of the hosts has a cache for caching data stored in at least one of the storage nodes. The host writes data corresponding to a write request to at least one remote non-volatile memory and carries out at least one storage processing function; data in the written-to node may then be made available for subsequent reading by a different one of the hosts. Examples of the storage processing function include compression, ECC computation, deduplicating, garbage collection, write logging, reconstruction, rebalancing, and scrubbing.

DYNAMIC MANAGEMENT OF EXPANDABLE CACHE STORAGE FOR MULTIPLE NETWORK SHARES CONFIGURED IN A FILE SERVER

Expandable cache management dynamically manages cache storage for multiple network shares configured in a file server. Once a file is written to a directory or folder on a specially designated network share, such as one that is configured for “infinite backup,” an intermediary pre-backup copy of the file is created in an expandable cache in the file server that hosts the network share. On write operations, cache storage space can be dynamically expanded or freed up by pruning previously backed up data. This advantageously creates flexible storage caches in the file server for each network share, each cache managed independently of other like caches for other network shares on the same file server. On read operations, intermediary file storage in the expandable cache gives client computing devices speedy access to data targeted for backup, which is generally quicker than restoring files from backed up secondary copies. 1. A method for managing storage for network shares configured in a file server , the method comprising:by the file server, receiving a write request comprising a first portion of a first file and designating a first network share configured in the file server as a storage destination for the write request;by a cache manager that executes on the file server, identifying one or more storage volumes configured in the file server that comprise a respective share-specific folder that stores data for the first network share and only for the first network share; 'by the cache manager, storing the first portion of the first file to a respective share-specific folder in the first storage volume;', 'if the cache manager determines that a first storage volume among the one or more storage volumes comprises sufficient storage space to store the first portion of the first file included in the write request,'} 'by the cache manager, storing the first portion of the first file to a respective share-specific folder in a second storage volume among the one or more ...

Storage Controller Cache Synchronization Method and Apparatus

A storage controller is provided. The storage controller includes a memory storing an indication of a current owner, a previous owner, and a preferred owner for each of one or more logical volumes. The storage controller is configured to write protect the logical volumes where the current owner and the preferred owner is the storage controller and the previous owner of the logical volumes was a different storage controller. For the logical volumes where the storage controller is the preferred but not the current owner, the storage controller is set as the current and preferred owner of the logical volumes that the different storage controller was the current but not the preferred owner for, storage controller is set as the previous owner of the logical volumes that the storage controller is the current and preferred owner of, and allowing read and write access to the one or more logical volumes.

ERROR CORRECTION IN SOLID STATE DRIVES (SSD)

A paging scheme for a Solid State Drive (SSD) error correction mechanism that exchanges portions of a parity component, such as a page, between SRAM and less expensive DRAM, which stores the remainder of a context of pages. A parity operation applies an XOR function to corresponding memory positions in the pages of the context. Dedicated error correction (parity) SRAM need only enough memory for portions of memory, typically a cache line of a page, upon which the parity operation (XOR) is operating. The remaining portions in the context are swapped, or paged out, by cache logic such that the entire context is iteratively processed (XORed) by the parity operation. 1. A method , comprising:partitioning a page into a plurality of cache lines, the page based on a memory space designated for error correction; a plurality of pages defining a context;storing corresponding cache lines of the pages of the context in a first memory area, the first memory area responsive to a parity operation for computing a parity value for the corresponding cache lines, a parity value for the context based on the plurality of pages;applying the parity operations to the cache lines stored in the first memory area; anditeratively replacing the cache lines in succession with other cache lines of the plurality of cache lines from a second memory area for applying the parity operation to each of the cache lines until the parity operation has been applied to all cache lines of the pages in the context, the second memory area sufficiently large for storing the entire context wherein iteratively replacing the cache lines and applying the parity operations decouples a required size of the first memory from the size of the page.2. The method of further comprising identifying the page claim 1 , the page defining a subdivision of memory upon which parity operations are applied.3. The method of wherein the cache lines correspond to at least first and second pages in the context claim 1 , further ...

FLUSHING HOST CACHE DATA BEFORE REBUILDING DEGRADED REDUNDANT VIRTUAL DISK

A storage management method includes receiving a degrade signal indicating a degraded state of a virtual disk associated with a host system. Rebuild-flush operations may be performed. The operations may include writing, to the virtual disk and also to a hot spare drive (HSP) associated with the virtual disk, valid-modified data, stored in a host storage cache, associated with the virtual disk. In contrast, valid-unmodified storage cache data associated with the virtual disk, may be written to the HSP only. After the rebuild-flush completes, the virtual disk may be rebuilt. During rebuild, however, any cached-LBA may be skipped where traditional RAID rebuild operations are performed for un-cached LBAs only. 1. A storage management method , comprising:receiving, by a host, a degrade signal indicating a DEGRADED state of a virtual disk associated with the host; writing, to the virtual disk and to a hot spare drive (HSP) associated with the virtual disk, valid-modified data, stored in a host storage cache, associated with the virtual disk; and', 'writing, to the HSP, valid-unmodified data, stored in the host storage cache, associated with the virtual disk; and, 'responsive to receiving the degrade signal, performing rebuild-flush operations comprising responsive to determining that the virtual disk LBA corresponds to valid cache data in the host storage cache, skipping to a next virtual disk LBA; and', regenerating user data associated with the LBA; and', 'storing rebuilt user data resulting from said regenerating to the HSP., 'responsive to determining that the virtual disk LBA does not correspond to valid cache data in the host storage cache], 'rebuilding the virtual disk, said rebuilding including, for each virtual disk logical block address (LBA)2. The method of claim 1 , further comprising:maintaining hash table data indicating virtual disk LBAs cached in the host storage cache.3. The method of claim 2 , wherein maintaining the hash table data includes:maintaining ...

STORAGE SYSTEM AND METHOD OF MANAGING VOLUMES THEREOF

A storage system includes a plurality of storage media and a method of managing volumes of the storage system is applied thereto. The method includes receiving a volume management request and correlation information between the volumes, and allocating storage spaces of the storage media to the volumes based on the correlation information between the volumes. The correlation information indicates information of the volumes in which the allocated storage media are physically isolated from each other. 1. A method of managing volumes of a storage system that comprises a plurality of storage media , the method comprising:receiving a volume management request and correlation information between the volumes; andallocating storage spaces of the storage media to the volumes based on the correlation information between the volumes,wherein the correlation information indicates information of the volumes in which the allocated storage media are physically isolated from each other.2. The method of claim 1 , wherein the volume management request comprises a request for creating a first volume and a request for creating a second volume claim 1 , and wherein the correlation information indicates that the first volume and the second volume constitute one redundant array of inexpensive disks (RAID).3. The method of claim 2 , wherein the receiving of the correlation information comprises:receiving first RAID information corresponding to the request for creating the first volume and second RAID information corresponding to the request for creating the second volume.4. The method of claim 2 , wherein when it is determined that the first volume and the second volume constitute one RAID claim 2 , the allocating comprises allocating storage spaces of different physical storage media to the first and second volumes.57-. (canceled)87. The method of claim claim 2 , wherein the information of the storage media comprises at least one of: (1) information about whether a defect occurs for each of ...

DYNAMIC MANAGEMENT OF EXPANDABLE CACHE STORAGE FOR MULTIPLE NETWORK SHARES CONFIGURED IN A FILE SERVER

Expandable cache management dynamically manages cache storage for multiple network shares configured in a file server. Once a file is written to a directory or folder on a specially designated network share, such as one that is configured for “infinite backup,” an intermediary pre-backup copy of the file is created in an expandable cache in the file server that hosts the network share. On write operations, cache storage space can be dynamically expanded or freed up by pruning previously backed up data. This advantageously creates flexible storage caches in the file server for each network share, each cache managed independently of other like caches for other network shares on the same file server. On read operations, intermediary file storage in the expandable cache gives client computing devices speedy access to data targeted for backup, which is generally quicker than restoring files from backed up secondary copies. 1. A system comprising:a file server in communication with a first computing device, wherein the file server comprises a plurality of storage volumes and is configured with a first network share accessible to the first computing device; and receive from the first computing device a read request for data in a first file in the first network share configured on the file server,', 'based on determining that the requested data is not available on the first network share, cause the data to be restored to the first network share from a secondary copy stored on a storage device that is distinct from the file server,', (i) identifying a second storage volume having sufficient storage capacity for the restored data, wherein the second storage volume is also associated with the first network share, and', '(ii) storing the restored data to the second storage volume, and, 'based on determining that a first storage volume associated with the first network share lacks sufficient storage space for the restored data, expand an amount of storage available to the first ...

Methods and systems for using a write cache in a storage system

Methods and systems for storing data at a storage device of a storage system are provided. The data is first temporarily stored at a first write cache and an input/output request for a persistence storage device used as a second write cache is generated, when an I/O request size including the received data has reached a threshold value. The data from the first cache is transferred to the persistence storage device and a recovery control block with a location of the data stored at the persistence storage device is updated. An entry is added to a linked list that is used to track valid data stored at the persistence storage device and then the data is transferred from the persistence storage device to the storage device of the storage system.

Storage device system for improving data input/output perfomance and data recovery information cache method

가. 청구범위에 기재된 발명이 속한 기술분야:본 발명은 데이타 입/출력 성능을 향상시키기 위한 기억장치 시스템 및 그에 따른 데이타 복구정보 캐시구현방법에 관한 것이다. end. TECHNICAL FIELD The present invention relates to a storage system for improving data input / output performance and to a method for implementing data recovery information cache. 나. 발명이 해결하려고 하는 기술적 과제:데이타 입출력 성능을 향상시키기 위해 데이타 복구정보(패러티정보) 리드동작의 오버헤드를 줄일 수 있는 기억장치 시스템 및 그에 따른 데이타 복구정보 캐시구현방법을 제공함에 있다. I. An object of the present invention is to provide a storage system capable of reducing the overhead of a data recovery information (parity information) read operation to improve data input / output performance, and a method of implementing the data recovery information cache accordingly. 다. 그 발명의 해결방법의 요지:데이타 복구에 필요한 정보를 블럭의 형태로 기억장치의 임의 영역에 연속적으로 저장하고 나머지 영역에 데이타를 저장하는 다수개의 고장 대응적인 기억장치와, 상기 각각의 기억장치와 제어기에 연결되는 캐시메모리들을 구비하는 기억장치 시스템에 있어서, 외부장치로부터 데이타 기록명령이 수신되면 상기 기억장치에서 독출된 데이타 복구정보가 해당 캐시메모리에서 히트하는가를 검사하고, 독출된 데이타 복구정보가 해당 캐시메모리에서 히트하는 경우 새로운 데이타 복구정보를 계산하여 상기 외부장치로부터 전송된 데이타와 함께 기록하는 한편, 독출된 데이타 복구정보가 해당 캐시메모리에서 히트하지 않을 경우 해당 기억장치에서 데이타 복구정보를 독출하여 새로운 데이타 복구정보를 계산한후 이를 상기 외부장치로부터 전송된 데이타와 함께 기록함을 특징으로 한다. All. Summary of Solution of the Invention: A plurality of fault-tolerant storage devices which continuously store information necessary for data recovery in the form of blocks in an arbitrary area of the storage device and store data in the remaining areas, In a storage system having cache memories connected to a controller, when a data write command is received from an external device, it is checked whether the data recovery information read from the storage hits the corresponding cache memory, and the read data recovery information is read. In the case of hit in the cache memory, new data recovery information is calculated and recorded together with the data transmitted from the external device. If the read data recovery information does not hit in the cache memory, the data recovery information is read from the storage device. Calculate new data recovery ...

A method for improving I/O performance of RAID system using a matrix stripe cache

본 발명은 행렬 스트라이프 캐쉬(Matrix Stripe Cache : MSC)를 통하여 입출력을 행 단위로 결정한 뒤 열 단위로 각 항목들을 읽기와 쓰기 별로 결합을 시도하여 입출력 개수를 줄임으로써 조각화된 쓰기의 성능을 향상시키며, 저하 모드의 작은 읽기 성능을 희생시켜서 일반 모드의 읽기 성능을 향상시킬 수 있도록 하는 행렬 스트라이프 캐쉬를 이용한 RAID 시스템의 입출력 성능 향상 방법을 제공한다. The present invention improves the performance of fragmented writes by reducing the number of inputs and outputs by determining inputs and outputs by row through a matrix stripe cache (MSC) and attempting to combine each item by column and read. It provides a method for improving the input / output performance of a RAID system using matrix stripe cache that can improve read performance in normal mode at the expense of small read performance in degraded mode. 본 발명은 디스크로 쓰기를 수행할 단위 MSC(Matrix Stripe Cache)로부터 행 결합 전 읽기쓰기 행렬인 rxw 행렬을 생성하는 제1과정; 상기 제1과정에서 생성된 행 결합 전 rxw 행렬로부터 행결합을 통해 최종 읽기 쓰기 행렬인 행 결합된 rxw 행렬을 생성하는 제2과정; 및 상기 제2과정에서 생성된 행 결합된 rxw 행렬을 바탕으로 읽기를 수행한 후, 상기 행 결합된 rxw 행렬의 각 행 별로 XOR 연산을 수행하고, 행 결합된 rxw 행렬의 각 열 별로 쓰기를 수행하는 제3과정;을 포함한다. The present invention provides a first process of generating an rxw matrix, which is a read-write matrix before row combining, from a unit matrix stripe cache (MSC) to write to a disk; A second step of generating a row-joined rxw matrix, which is a final read / write matrix, by row-combining from the row-combining rxw matrix generated in the first step; And read based on the row-coupled rxw matrix generated in the second process, perform an XOR operation for each row of the row-coupled rxw matrix, and perform a write for each column of the row-coupled rxw matrix. To include; a third process. 단위 행렬 스트라이프 캐쉬, RAID, 입출력 성능 향상 Improved Unit Matrix Stripe Cache, RAID, and I / O Performance

A method for improving i/o performance of raid system using a matrix stripe cache

본 발명은 행렬 스트라이프 캐쉬(Matrix Stripe Cache : MSC)를 통하여 입출력을 행 단위로 결정한 뒤 열 단위로 각 항목들을 읽기와 쓰기 별로 결합을 시도하여 입출력 개수를 줄임으로써 조각화된 쓰기의 성능을 향상시키며, 저하 모드의 작은 읽기 성능을 희생시켜서 일반 모드의 읽기 성능을 향상시킬 수 있도록 하는 행렬 스트라이프 캐쉬를 이용한 RAID 시스템의 입출력 성능 향상 방법을 제공한다. 본 발명은 디스크로 쓰기를 수행할 단위 MSC(Matrix Stripe Cache)로부터 행 결합 전 읽기쓰기 행렬인 rxw 행렬을 생성하는 제1과정; 상기 제1과정에서 생성된 행 결합 전 rxw 행렬로부터 행결합을 통해 최종 읽기 쓰기 행렬인 행 결합된 rxw 행렬을 생성하는 제2과정; 및 상기 제2과정에서 생성된 행 결합된 rxw 행렬을 바탕으로 읽기를 수행한 후, 상기 행 결합된 rxw 행렬의 각 행 별로 XOR 연산을 수행하고, 행 결합된 rxw 행렬의 각 열 별로 쓰기를 수행하는 제3과정;을 포함한다. 단위 행렬 스트라이프 캐쉬, RAID, 입출력 성능 향상

Semiconductor storage device and control method for same

신뢰성을 높이고, 또한, 하나의 계층으로 SSD를 효율적으로 제어한다. 본 발명에 따른 반도체 기억 장치는, 프라이머리 메모리(3)와, 프라이머리 메모리(3)에 저장되는 데이터에 대응하는 데이터가 저장되는 미러 메모리(4)와, 버퍼 메모리(5) 중 적어도 하나의 메모리와, 적어도 하나의 메모리를 제어하여, 적어도 하나의 메모리에 데이터를 저장하고, 적어도 하나의 메모리로부터 데이터를 판독하는 제어 장치(2)를 구비한다.

Method and apparatus for writing data to a disk array

A method for writing data to a RAID 5 configuration of hard disks writes two or more items of data to a data stripe together. The method includes the determining of the suitability of data items to be written together, the storing of the new data items to temporary buffers, the reading of the original data and parity from the hard disk to the temporary buffers, the modification of the parity and the writing of the new data and new parity to the hard disks.

Semiconductor storage and its control method

提高可靠性且以一个分层高效地控制SSD。本发明所涉及的半导体存储装置具备：主存储器(3)、保存有与主存储器(3)中保存的数据对应的数据的镜像存储器(4)以及缓冲存储器(5)中的至少一个存储器；以及控制装置(2)，其控制至少一个存储器，将数据保存在至少一个存储器中，从至少一个存储器读出数据。

Fault tolerant storage device with cache

Improved disk array system having special parity groups for data blocks with high update activity

In a digital storage disk array system in which parity blocks are created and stored in order to be able to recover lost data blocks in the event of failure of a disk, high-activity parity groups are created for data blocks having high write activity and low-activity parity groups are created for data blocks not having high write activity. High-activity parity blocks formed from the high-activity data blocks are then stored in a buffer memory of a controller rather than on the disks in order to reduce the number of disk accesses during updating.

Storage device, control method thereof, and program

Updating and reading data and parity blocks in a shared disk system with request forwarding

A system and method for updating data. A first processing unit, such as an adaptor, receives a data update to a data block in a first storage device, such as a hard disk drive. Parity data for the data block is maintained in a second storage device, e.g., another hard disk drive. A parity group is comprised of the data block and corresponding parity data. The first processing unit determines whether the first processing unit controls access to the parity group, i.e., the state of lock ownership. The first processing unit transmits the data update to a second processing unit after determining that the first processing unit does not control access to the parity group. The second processing unit, another adaptor, performs an update after receiving the data update from the first processing unit. The first processing unit performs an update after determining that the first processing unit controls access to the parity group.

Polar codes for efficient encoding and decoding in redundant disk arrays

An improved technique applies polar codes to storage data to improve the reliability of a storage system that uses high-performance, solid-state disks as part of a RAID group for storing frequently-accessed data. Along these lines, a high-performance storage system having n solid-state disks assigns k of those disks as payload disks. The storage system partitions the payload data into a data vector that has data symbols. The storage system then applies, to the k payload symbols, a (n, k) polar code generator matrix derived from k rows of the [log 2 n] -times Kronecker product of the matrix (formula(I)) it to produce n encoded symbols and stores each of the encoded payload symbols in a solid-state disk of the RAID group.

Storage device and storage device write access processing method

The present invention allows the processing mode for write access operations to be set independently and respectively for prescribed units. The processing modes for handling write access are set previously for each of the volumes 6 A and 6 B. If the cache memory is functioning normally, write access operations to the respective volumes 6 A and 6 B are processed by means of an after-write method as illustrated in FIG. 1 (a). If an abnormality has occurred in the cache memory, then write access operations to the volumes 6 A and 6 B are processed by means of a method previously selected from a write-through method as illustrated in FIG. 1 (b) or a non-redundant storage type write-after method as illustrated in FIG. 1 (c). By using different processing modes for write access, for each of the volumes 6 A and 6 B, it is possible to set a suitable processing mode respectively for each of the prescribed units, in accordance with the composition of the storage system, the operation configuration, and the like.

Solid-state disk cache-assisted redundant array of independent disks

A system including a write module to receive first data for writing over second data stored on a first member of a stripe of a RAID. A read module reads the second data and first parity from a SSD or the RAID. Before receiving third data for writing over fourth data stored on a second member of the stripe, the read module reads the fourth data from the second member and stores the fourth data in the SSD. A parity module generates second parity based on the first data, the second data, and the first parity. The write module writes the second parity on the SSD. On receiving the third data, the parity module generates the third parity based on the third data, the fourth data, and the second parity.

Method of improving input and output performance of raid system using matrix stripe cache

这里公开了一种使用矩阵条带高速缓存器(MSC)来改进独立磁盘冗余阵列(RAID)系统的输入/输出(I/O)性能的方法，所述方法包括：第一步骤，用于通过将执行对磁盘的写入的单元MSC，生成在行组合之前呈现的基本rxw矩阵，即读取和写入矩阵；第二步骤，用于通过行组合，根据在第一步骤中生成的行组合之前的rxw矩阵来生成rxw矩阵，即最终的读取和写入矩阵；以及第三步骤，基于第二步骤中生成的行组合后的rxw矩阵来执行读取、针对基于行的行组合后的rxw矩阵来执行XOR操作、以及基于列的行组合后的rxw矩阵来执行写入。

System and method for emulating block appended checksums on storage devices by sector stealing

A system and method for emulating conventional block appended checksums on storage devices that generally do not support such checksums in a block is provided. A grouping of data sectors with one or more checksum sectors is generated. This grouping is mapped to/from a file system data structure associated with a traditional block appended checksum disk drive.

Nonvolatile media dirty region tracking

System and methods for RAID writing and asynchronous parity computation

A computer storage management system for managing a first plurality of data storage units, the system including: (a) an asynchronous parity computation manager which, responsive to a write operation in which an incoming data portion is to be written into an individual storage unit from among the storage units, deposits the incoming value in the individual storage unit and stores a copy of the data element in a pre-parity storage area, and wherein asynchronously with depositing the incoming value in the individual storage unit, the asynchronous parity computation manager is operative to compute parity data corresponding to the incoming data portion and to other data portions which are associated with the incoming data portion and to store the parity data; and (b) a post-loss data recovery manager operative to recover lost data including determining whether at least one parity value associated with at least one data portion within said lost data is not current and, for at least one non-current parity, using information stored in the pre-parity storage area to generate, after said lost data has been lost, a current parity to replace said non-current parity and using said current parity to recover said lost data.

Storing data on storage nodes

用于在存储节点上存储数据的方法、系统和装置，包括在计算机存储介质上编码的计算机程序。在一个方面中，一种方法包括接收将跨越各自包括高速缓存的多个存储节点存储的文件。通过各自在不同存储节点上存储文件的部分存储文件。向第一存储节点的高速缓存写入第一部分，直至确定第一存储节点的高速缓存为满。响应于确定第一存储节点的高速缓存为满，选择不同的第二存储节点。为文件的每个部分记录该部分的位置，该位置至少指示存储该部分的存储节点。

Write cache management method and apparatus

A method for destaging data from a memory of a storage controller to a striped volume is provided. The method includes determining if a stripe should be destaged from a write cache of the storage controller to the striped volume, destaging a partial stripe if a full stripe write percentage is less than a full stripe write affinity value, and destaging a full stripe if the full stripe write percentage is greater than the full stripe write affinity value. The full stripe write percentage includes a full stripe count divided by the sum of the full stripe count and a partial stripe count. The full stripe count is the number of stripes in the write cache where all chunks of a stripe are dirty. The partial stripe count is the number of stripes where at least one chunk but less than all chunks of the stripe are dirty.

Method and system for minimizing writes and reducing parity updates in a raid system

A method and system for updating stored data with received data in a cache associated with the data storage system is provided, where the data storage system comprises N data storage drives, where data and calculated parity are striped across N data storage drives, where a stripe comprises multiple data sectors on each of N data storage drives. An associated cache is provided with the data storage system into which data is received. The data in the cache is periodically examined to determine if the cache includes all sequential data sectors contained within a complete stripe within the data storage system. Parity is calculated for the complete stripe by first calculating a range of sectors between which all sectors received into the cache for the complete stripe fall. Next, only those sectors within the range of sectors which are not included in the data in the cache for the complete stripe are read from the N data storage drives into the cache. Finally, the range of sectors in the cache for the complete stripe are logically combined. The parity is calculated such that input/output operations within said data storage system are minimized.

Dynamic management of expandable cache storage for multiple network shares configured in a file server

Expandable cache management dynamically manages cache storage for multiple network shares configured in a file server. Once a file is written to a directory or folder on a specially designated network share, such as one that is configured for “infinite backup,” an intermediary pre-backup copy of the file is created in an expandable cache in the file server that hosts the network share. On write operations, cache storage space can be dynamically expanded or freed up by pruning previously backed up data. This advantageously creates flexible storage caches in the file server for each network share, each cache managed independently of other like caches for other network shares on the same file server. On read operations, intermediary file storage in the expandable cache gives client computing devices speedy access to data targeted for backup, which is generally quicker than restoring files from backed up secondary copies.

Method for processing a cache barrier commend for a disk array and device for the same

레이드 컨트롤러가, 명령시퀀스를 생성하는 단계 및 상기 레이드 컨트롤러가, 상기 명령시퀀스에 포함된 제1캐시배리어 명령어를 확인한 경우에는, 상기 명령시퀀스 내에서 상기 제1캐시배리어 명령어 이후에 배치되어 있는 제1쓰기 명령어를 레이드를 구성하는 임의의 디스크에게 전송하기 이전에, 적어도 한 개의 캐시배리어 명령을 상기 임의의 디스크에게 전송하는 단계를 포함하는, 레이드 컨트롤러 제어방법을 공개한다.

Method and apparatus for controlling a disk cache in a disk array system

본 발명은 디스크어레이(disk array) 시스템에서의 디스크 캐쉬(cache) 관리 장치 및 관리 방법에 관한 것이다. 디스크 캐쉬 관리 구조는 크게 해시 테이블(hash table), 스트라이프 택(stripe tag), 캐쉬 택(cache tag)으로 구성된다. 해시 테이블은 해시 엔트리들의 배열 구조로 구성되며, 각 해시 엔트리는 스트라이프 택들을 이중 연결 리스트로 연결할 수 있는 이중 포인터로 구성된다. 스트라이프 택은 스트라이프 단위로 할당되며, 스트라이프 관련 정보와 해당 스트라이프에 속하는 데이터나 패리티가 캐쉬에 저장되는 경우 이를 관리하는 해당 캐쉬 택들을 연결하는 이중 포인터로 구성된다. 캐쉬 택은 데이터 관리에 필요한 정보와 데이터가 저장된 메모리 주소로 구성된다. 해시 함수는 특정 블록이 속하는 스트라이프의 번호를 입력으로 받아 해당하는 해시 엔트리의 번호를 산출한다. 해시 엔트리가 결정되면 이중 포인터를 이용하여 처음부터 순차적으로 연결된 스트라이프 택들의 스트라이프 번호와 특정 블록이 속하는 스트라이프 번호를 비교하여 해당 스트라이프 택을 결정한다. 이후, 해당 스트라이프 택의 캐쉬 택 리스트들에 연결된 스트라이프를 구성하는 캐쉬 택들의 블록 번호를 검색하고자 하는 블록 번호와 순차적으로 비교함으로써 해당 캐쉬 택을 결정한다. 결정된 캐쉬 택이 관리하는 캐쉬 라인을 구성하는 블록들의 상태값을 참조함으로써 특정 블록의 캐슁 여부가 결정된다. 즉, 본 발명은 디스크 복구 모드의 경우 요구된 블록을 제외한 스트라이프에 속하는 나머지 블록들에 대한 캐슁 여부를 결정하기 위하여 캐쉬를 검색할 때 일단 오류 데이터의 캐쉬 검색을 통해 스트라이프 택이 결정되기 때문에 나머지 블록들에 대한 검색은 해당 스트라이프 택에서 바로 결정될 수 있다. 따라서, 단일 택을 이용하는 구조에 비해 복구 모드에서의 캐쉬 검색 과정이 간편하다. 또한, 패리티를 관리하는 캐쉬 택을 별도로 관리하지 않고 동일한 스트라이프 택에서 관리하기 때문에 효율적으로 데이터를 복구할 수 있다. 그리고, 복구가 수행되는 동안 해당 스트라이프에 대한 일반적인 입출력 요구의 처리의 중단을 위한 스트라이프 단위의 락도 별도의 자료구조나 과정이 필요 없이 스트라이프 택을 결정하는 과정에서 직접 처리함으로써 보다 간편하게 해결될 수 있다. The present invention relates to a disk cache management apparatus and management method in a disk array system. The disk cache management structure is largely composed of a hash table, a stripe tag, and a cache tag. The hash table consists of an array of hash entries, and each hash entry consists of a double pointer that can link stripe tags into a double linked list. The stripe tack is allocated on a stripe basis, and is composed of a double pointer that connects stripe related information and corresponding cache tacks managing data or parity belonging to the stripe when it is stored in the cache. The cache tag consists of information necessary for data management and a memory address where data is stored. The hash function takes as input the number of stripes to which a particular block belongs and calculates the number of the corresponding ...

Error correction in solid state drives (SSD)

A paging scheme for a Solid State Drive (SSD) error correction mechanism that exchanges portions of a parity component, such as a page, between SRAM and less expensive DRAM, which stores the remainder of a context of pages. A parity operation applies an XOR function to corresponding memory positions in the pages of the context. Dedicated error correction (parity) SRAM need only enough memory for portions of memory, typically a cache line of a page, upon which the parity operation (XOR) is operating. The remaining portions in the context are swapped, or paged out, by cache logic such that the entire context is iteratively processed (XORed) by the parity operation.

Flushing host cache data before rebuilding degraded redundant virtual disk

A storage management method includes receiving a degrade signal indicating a degraded state of a virtual disk associated with a host system. Rebuild-flush operations may be performed. The operations may include writing, to the virtual disk and also to a hot spare drive (HSP) associated with the virtual disk, valid-modified data, stored in a host storage cache, associated with the virtual disk. In contrast, valid-unmodified storage cache data associated with the virtual disk, may be written to the HSP only. After the rebuild-flush completes, the virtual disk may be rebuilt. During rebuild, however, any cached-LBA may be skipped where traditional RAID rebuild operations are performed for un-cached LBAs only.

Storage device system operating based on system information, and method for controlling thereof

The storage device system has a storage device to which system information related to the storage device system is written, and a determination unit determining the presence and absence of system information errors before operation based on system information written to the storage device is conducted. When an error is determined as a result of the determination of the system information written to one storage device of a plurality of storage devices, storage device can be closed, and system information written to another storage device is determined for the presence and absence of errors.

Storage unit subsystem

When receiving a write request from a processor, a control unit checks the condition of existence (or the presence/absence) in a cache for information necessary for generation of an updated value of a parity record, receives write data and reports the completion of the write request to the processor. In asynchronism with the write request from the processor, the control unit performs a load process for that information among the information necessary for generation of the updated value of the parity record which may be prepared in asynchronism with the write request from the processor and a write after process for the updated value of the parity record.

Determine failed components in fault-tolerant memory

According to an example, a failed component in a fault-tolerant memory fabric may be determined by transmitting request packets along a plurality of routes between the redundancy controller and a media controller in periodic cycles. The redundancy controller may determine whether route failures for all of the plurality of routes have occurred within a number of consecutive periodic cycles. In response to determining that route failures for all of the plurality of routes have occurred within a number of consecutive periodic cycles, the media controller is established as failed. In response to determining that route failures for less than all of the plurality of routes have occurred within the number of consecutive periodic cycles, a fabric device is established as failed.

Write cache sorting

A method of managing a non-volatile memory system is described where data elements stored in a buffer are characterized by attributes and a write data tag is created for the data elements. A plurality of write data tag queues is maintained so that different data attributes may be applied as sorting criteria when the data elements are formed into pages for storage in the non-volatile memory. The memory system may be organized as a RAID system and a write data tag queue may be associated with a specific RAID group such that the data pages may be written from a buffer to the non-volatile memory in accordance with the results of sorting each write data queue. The data elements stored in the buffer may be received from a user, or be read from the non-volatile memory during the performance of system overhead operations.

System and method for handling writes in HDD using 4K block sizes

In a disk drive that uses large block sizes (e.g., 4 KB) for storing data and that responds to read and write requests from a client that uses small block sizes (e.g., 512 bytes), at least the starting and ending 4K blocks of read data are cached. Since much disk data that is the subject of a write request is first read, upon a subsequent write request the drive controller determines whether the starting and ending blocks are in cache and if so, writes new data to those blocks, calculates a full ECC for them, and then calculates ECC for intervening blocks and writes new data to the intervening blocks. If both starting and ending blocks are not in cache the drive controller executes either a high data integrity routine or a high performance routine as chosen by the user.

Method for providing parity in a raid sub-system using a non-volatile memory

The present invention is a method for providing error correction for an array of disks (828) using non- volatile random access memory (NV-RAM) (816). Non-volatile RAM (816) is used to increase the speed of RAID recovery from a disk error(s). This is done by listing of all blocks for which the parity is possibly Inconsistent. This list of blocks is much smaller than the total number of parity blocks (820) in the RAID. The total number of parity blocks (820) in the RAID (828) is in the range of hundreds of thousands. Knowledge of the number of parity blocks that are possibly inconsistent makes it possible to fix only those few blocks, identified in the list, resulting in a significant time savings. The technique for safely writing to a RAID with a broken disk is complicated. In this technique, data that can become corrupted is copied into NV-RAM (816) before the potentially corrupting operation is performed.

Host base raid-5 and nv-ram integrated system

(57)【要約】 【課題】 計算システムにおける冗長記憶装置アレイの 書込み時間を短縮する。 【解決手段】 ＲＡＩＤディスク・アレイに配置された 冗長記憶装置を利用するコンピュータ・システムにおい て、システム・メモリから作成されたメモリ・キャッシ ュおよびディスク・アレイを用いて、コンピュータ・シ ステムにおいてデータを記憶する。チェックポイント・ モジュールが計算システム内の障害を検出して障害指示 を発生する。キャッシュ・マネージャは、第１モードに おいてデータおよびパリティをメモリ・キャッシュに書 き込み、第２モードでデータおよびパリティを記憶装置 に書き込む。障害指示に応答して、チェックポイント・ モジュールは、キャッシュ内に含まれているデータをデ ィスク・アレイにコピーし、キャッシュ・マネージャを 第１モードから第２モードに切り替える。

Method and apparatus for reading and writing data in file system

Embodiments of the present invention disclose a method and an apparatus for reading and writing data in a file system, which are applicable to the field of communication technologies. In the embodiments of the present invention, the file system supports file-level redundancy algorithm operations of independent disks; after receiving a file read/write request, the file system determines a read/write location of the data to be read/written in the data strip, sequentially caches the to-be-read/written data information corresponding to at least one data strip, and processes the cached data information of at least one data strip. In this way, after the to-be-read/written data information corresponding to a complete data strip is cached, the data is read/written by using a data strip as a unit, and thereby improving efficiency of reading/writing data.

Systems and methods for internal disk drive data compression

本發明關於資料儲存壓縮的系統及方法。

Apparatus and method for secure writing to multiplexed redundant storage

An arrangement of apparatus for safely writing data and parity to multiply-redundant storage comprises a first storage component operable to store at least a first mark in a storage device to index uniquely a pattern to be written by at least a data write; a write component operable to perform the at least data write; a further storage component operable to overwrite a mark in the storage device with at least a further mark to index uniquely a pattern to be written by a parity write; and a further write component operable to perform the parity write. Preferably, the first storage component comprises a second storage component operable to overwrite said at least first mark in said storage device with a second mark to index a pattern to be written by a first parity write; and the write component is further operable to perform the first parity write.

Host-based RAID-5 and NV-RAM integration

In a computing system utilizing redundant storage devices arranged in the RAID disk array, data is stored in the computing system using a memory cache created from system memory and the disk array. A checkpoint module detects a fault in the computing system and generates a fault indication, and a cache manager writes data and parity to the memory cache in a first mode, and writes data and parity to the storage device in a second mode. In response to the fault indication, the checkpoint module copies the data contained in the cache to the disk array, and switches the cache manager from the first mode to the second mode.

Method and system for calculating single and dual parity for networked storaged elements

A method of calculating single and dual parity for a networked array of storage elements is presented. The method includes deriving a first set of n relationships where each of the first set of n relationships consists of an XOR statement equaling zero. Each of the first set of n relationships contains n data symbols from n storage elements and one parity symbol from a first set of parity symbols. The method also includes deriving a second set of n+1 relationships where each of the second set of n+1 relationships consists of an XOR statement equaling zero, containing at least n−1 data symbols from at least n−1 storage elements and one parity symbol from a second set of parity symbols. Using both the first and second sets of derived relationships, scripts are generated to resolve unresolved symbols resulting from possible single- and dual-storage element failure combinations.

Data protection in a random access disk array

A disk array memory system comprises: a plurality of disks in a disk array for storage of content data and parity data in stripes, content data in a same stripe sharing parity bits of said parity data, each disk having a spare disk capacity including at least some of a predefined array spare capacity, said array spare capacity providing a dynamic space reserve over said array to permit data recovery following a disk failure event; a cache for caching content data prior to writing to said disk array; and a controller configured to select a stripe currently having a largest spare stripe capacity, for a current write operation of data from said cache, thereby to write all said data of said current write operation on a same stripe, thereby to maximize sharing of parity bits per write operation and minimize separate parity write operations.

System and method for maintaining a data redundancy scheme in a solid state memory in the event of a power loss

本发明的实施例涉及降低数据冗余方案的电力失效安全保护所需的备用电力的量的系统和方法。该数据冗余方案，诸如RAID，被实现在固态存储装置中，其中新写入数据被积累并且与奇偶数据一起写入。因为不能确保新写入数据以条大小的整数倍到达，所以当失去供电时可能不存在用于新写入数据的完整条。各个实施例使用截断的RAID条(每个条有更少的存储元件)以在发生供电故障时储存缓存的写入数据。即使可能不存在写入数据的完整条，该方法也允许系统在供电故障缓存器清除的情况下维持RAID奇偶校验数据保护，从而降低在失去电力事件中维持奇偶保护所需要的备用电力的量。

Data storage system with dedicated allocation of parity storage and parity reads and writes only on operations requiring parity information

Table Vectored Parity (TVP) of the present invention is a new method for the allocation of parity check information in multi disk storage systems. This technique permits an optional selection by the end user to store parity check information on a subset of any number of disks ranging from 1 to N, where there are N disks in the system.

Storage unit subsystem

When receiving a write request from a processor, a control unit checks the condition of existence (or the presence/absence) in a cache for information necessary for generation of an updated value of a parity record, receives write data and reports the completion of the write request to the processor. In asynchronism with the write request from the processor, the control unit performs a load process for that information among the information necessary for generation of the updated value of the parity record which may be prepared in asynchronism with the write request from the processor and a write after process for the updated value of the parity record.

Storage unit subsystem

When receiving a write request from a processor, a control unit checks the condition of existence (or the presence/absence) in a cache for information necessary for generation of an updated value of a parity record, receives write data and reports the completion of the write request to the processor. In asynchronism with the write request from the processor, the control unit performs a load process for that information among the information necessary for generation of the updated value of the parity record which may be prepared in asynchronism with the write request from the processor and a write after process for the updated value of the parity record.

Fast destaging method using parity engine

The present invention relates to the fast destaging method using a parity engine, and more particularly to the fast destaging method for constituting and administering the cache of disk array in order to minimize lowering of write performance which occurs in high-speed disk array controller using VRAM parity engine. According to the invention, the disk cache is composed of the read cache, the write cache and the destaging cache. The write caching is processed as being divided into the write cache and the destaging cache. The destaging cache, which has just one more block for mid parity to its data block, uses less memory and enables the write cache to be allocated with more blocks, and thereby it can improve hit ratio of cache. Write requests are first stored on the write cache, and if the write cache is full, they move blocks that would be least used thereafter into the destaging cache. Once destaging is requested, it is practicable with one parity calculation and two write operations by selecting blocks that is least recently used. Also in destaging, block parity calculation can increase its speed and relieve the processor burden by using a VRAM based parity engine which has its dual ports.

Method, storage controller and system for efficiently destaging sequential i/o streams

Method and systems for flyby raid parity generation

Methods and structure for improved RAID storage subsystem performance in high bandwidth, a full stripe operating modes. The invention provides for flyby parity generation within the RAID storage controller for use of a high-speed memory buffer dedicated to XOR parity generation. As full stripe host supplied write data is transferred via a high-speed I/O channels from a host system to a data cache memory within the storage controller, flyby XOR parity generation using the high-speed XOR buffer generates the corresponding parity block. The generated parity block is then transferred to a corresponding location in data cache memory without the need for reading host supplied data blocks solely for purposes of generating parity.

Disk subsystem

The present invention creates real data and parity data using plural hard disk control units without changing the number of disk adapters per hard disk control unit and distributes and stores data in a hard disk. While it is being requested that a disk utilization rate is increased maintaining the failure resistance of the hard disk, and, at the same time, to support the combination of the real data+parity data as before, it is desirable that the number of adapters that comprise the hard disk control unit should not be changed. According to the present invention, the number of hard disks that comprise RAID can be changed without changing the number of disk adapters per hard disk control unit.

Safe write to multiply-redundant storage

An arrangement of apparatus for safely writing data and parity to multiply-redundant storage comprises a first storage component operable to store at least a first mark in a storage device to index uniquely a pattern to be written by at least a data write; a write component operable to perform the at least data write; a further storage component operable to overwrite a mark in the storage device with at least a further mark to index uniquely a pattern to be written by a parity write; and a further write component operable to perform the parity write. Preferably, the first storage component comprises a second storage component operable to overwrite said at least first mark in said storage device with a second mark to index a pattern to be written by a first parity write; and the write component is further operable to perform the first parity write.

Disk processor and recording medium

(57)【要約】 【課題】 ディスク処理におけるアクセス速度を向上さ せること。 【解決手段】 ＨＤＤ６および７の各ディスクを外周側 のゾーンと内周側のゾーンからなる２ドライブに分割 し、読み書きの速度が速い外周側のゾーンを高速部と し、読み書きの速度が遅い内周側のゾーンを低速部とす る。ＲＡＭ３内の制御プログラムにしたがって、ＣＰＵ １に、ＨＤＤ６，７のいずれか一方の高速部と他方の低 速部とがペアになるようにミラーリングを実行させる。 これによって、一方のディスクのアクセスの速いゾーン と他方のディスクのアクセスの遅いゾーンのアクセス速 度の差が常に大きくなるようにしてミラーリングするこ とができ、アクセスの速いほうのディスクが先にREADY となって、アクセスの遅いほうのディスクの書き込み完 了を待たずに、次のデータの書き込み、または読み出し が可能となり、アクセス効率が向上する。

Buffer for RAID controller with disabled post write cache

Enhancing management of controllers in a RAID system when a post-write-cache of a is disabled, by supplying a stripe buffer that stores sequential write requests—and before such requests are actually written in to the physical disc drives. The stripe buffer can temporarily store data, until the data level reaches the stripe buffer size. Thereafter, contents of the stripe buffer can be flushed onto disc.

Journaling technique for write transactions to mass storage

A technique includes writing blocks of data from a plurality of servers to an array of disks that are shared in common by the servers. Prior to the writing in each block of data to the array of disks, the method includes storing in a journal a copy of the block of data to be written to the array of disks. Also stored in the journal is at least one header, and this header(s) indicates that the copy was successfully stored in the journal.

Intelligent disk-cache memory

Method and apparatus for intelligently caching data in an intelligent disk subsystem connected to a main computer having a main memory. The disk subsystem includes a disk-cache memory having a first and a second memory bank. A first copy and a second copy of data are held in the first and second memory banks, respectively, wherein the first memory bank is coupled to a first battery and the second memory bank is coupled to a second battery. A detected failure occurring in either memory bank or either battery causes either the first copy or the second copy of data to be read, based on where a detected failure occurred. In one embodiment, successive read operations are routed to alternating memory banks. In one embodiment, read operations going to disk devices and returning data to the disk-cache memory are given a higher priority than write operations. In one embodiment, only write operation data are cached in the cache memory, but either read or write operations are completed using the data held in the cache memory.

Storage system

A redundant array of inexpensive disks (RAID) system includes a plurality of defect-adaptive memory devices for sequentially storing information needed for data recovery in a predetermined region of a recording medium in the form of block, and storing data in a region other than the predetermined region. A plurality of caches are connected to the adaptive memory devices to store information blocks needed for data recovery, the information blocks being read from a predetermined memory device. A controller is connected to each adaptive memory device and cache to control the writing and reading of data and information needed for data recovery in each memory device, calculate information needed for recovery of data read from each memory device, and store the information needed for recovery of data calculated in a predetermined cache.

Data management architecture

A performance optimized RAID Level 3 storage access controller with a unique XOR engine placement at the host/network side of the cache. The invention utilizes multiple data communications channels and a centralized cache memory in conjunction with this unique XOR placement to maximize performance and fault tolerance between a host network and data storage. Positioning the XOR engine at the host/network side of the cache allows the storage devices to be fully independent. Since the XOR engine is placed in the data path and the parity is generated in real-time during cache write transfers, the bandwidth overhead is reduced to zero. For high performance RAID controller applications, a system architecture with minimal bandwidth overhead provides superior performance.

System and method for handling writes in HDD using 4K block sizes

In a disk drive that uses large block sizes (e.g., 4 KB) for storing data and that responds to read and write requests from a client that uses small block sizes (e.g., 512 bytes), at least the starting and ending 4K blocks of read data are cached. Since much disk data that is the subject of a write request is first read, upon a subsequent write request the drive controller determines whether the starting and ending blocks are in cache and if so, writes new data to those blocks, calculates a full ECC for them, and then calculates ECC for intervening blocks and writes new data to the intervening blocks. If both starting and ending blocks are not in cache the drive controller executes either a high data integrity routine or a high performance routine as chosen by the user.

Storage system

Parity-based raid system configured to protect against data corruption caused by the occurrence of write holes

A RAID system is provided in which the RAID controller of the system causes a predetermined number, N, of IO commands to be queued in a memory element, where N is a positive integer. After the N IO commands have been queued, the RAID controller writes N locks associated with the N IO commands in parallel to a service memory device. The RAID controller then writes N stripes of data and parity bits associated with the N IO commands to the PDs of the system to perform striping and parity distribution. If a catastrophic event, such as a power failure, occurs, the RAID controller reads the locks from the service memory device and causes parity to be reconstructed for the stripes associated with the locks. These features improve write performance while preventing the occurrence of data corruption caused by write holes.

Storage system cache with flash memory in a raid configuration that commits writes as full stripes

Embodiments of the invention relate to a storage system cache with flash memory units organized in a RAID configuration. An aspect of the invention includes a storage system with a storage cache that includes flash memory units organized in an array configuration. The storage system further includes an array controller that manages data access and data operations for the flash memory units and organizes data as full array stripes. The storage system also includes a storage cache controller, that includes a block line manager that buffers write data to be cached for a write operation until the storage cache controller has accumulated an array band, and commits write data to the array controller as full array stripes. The storage cache controller determines whether to store write data for a write in the storage cache and/or in the primary storage device and whether to access read data from the storage cache or from the primary storage device.

Method for providing parity in a raid sub-system using a non-volatile memory

The present invention is a method for providing error correction for an array of disks (828) using non- volatile random access memory (NV-RAM) (816). Non-volatile RAM (816) is used to increase the speed of RAID recovery from a disk error(s). This is done by listing of all blocks for which the parity is possibly Inconsistent. This list of blocks is much smaller than the total number of parity blocks (820) in the RAID. The total number of parity blocks (820) in the RAID (828) is in the range of hundreds of thousands. Knowledge of the number of parity blocks that are possibly inconsistent makes it possible to fix only those few blocks, identified in the list, resulting in a significant time savings. The technique for safely writing to a RAID with a broken disk is complicated. In this technique, data that can become corrupted is copied into NV-RAM (816) before the potentially corrupting operation is performed.

Zone aware request scheduling and data placement

A method begins with receiving an encoded data slice that has associated therewith a slice name that is representative of a dispersed storage network (DSN) logical address. The method continues with accessing a DSN address to memory device mapping based on the DSN logical address to identify a memory device of the storage unit. The method continues with retrieving a logical zone to physical address space mapping of the identified memory device. The method continues with determining information regarding the encoded data slice and a logical zone of the memory device from the logical zone to physical address space mapping based on the encoded data slice information. The method continues with generating a physical address within the identified logical zone for storing the encoded data slice. The method continues with storing the encoded data slice within the identified memory device at the physical address.

리던던트 2차 스토리지 캐시의 재구성

제 1 스토리지 디바이스와 제 2 스토리지 디바이스를 포함하는 리던던트 2차 스토리지 캐시를 재구성하기 위한 시스템 및 기법이 설명된다. 1차 스토리지 디바이스의 지역과 연관되고 제 1 스토리지 캐시 디바이스에 의해 저장되는 정보의 일부의 유효성을 표시하는 메타데이터 엔트리가 수신된다. 1차 스토리지 디바이스의 지역과 연관되는 정보의 일부의 유효성이 수립되는 경우, 제 1 스토리지 캐시 디바이스에 의해 저장되는 정보의 일부와 연관되는 1차 스토리지 디바이스의 지역에 지역 잠금이 요청된다. 또한, 1차 스토리지 디바이스의 지역과 연관되는 정보의 일부 및 대응 메타데이터 엔트리는 제 1 캐시 저장 디바이스로부터 제 2 스토리지 캐시 디바이스로 카피되어 제 2 스토리지 캐시 디바이스를 재구성한다.

Elastic cache with single parity

The invention provides an elastic or flexible SSD cache utilizing a hybrid RAID protocol combining RAID-0 protocol for read data and RAID-5 single parity protocol for write data in the same cache array. Read data may be stored in window sized allocations using RAID-0 protocol to avoid allocating an entire RAID stripe for read cache data. In the same SSD volume, dirty write data is stored in row allocations using RAID-5 protocol to provide single parity for the dirty write data. Read data is typically stored a window from the physical device having the largest number of available windows. Write data is stored in a row including the next available window in each arm, which decouples the window structure of the rows from the stripe configuration of the physical memory devices.

記憶制御装置及び記憶装置の障害検出方法

【課題】本発明の記憶制御装置は、単一の保証コードでは検出することのできない障害がデータに生じた場合でも、その障害を検出して修復することができる。 【解決手段】 記憶制御装置１のコントローラ２は、ホスト４からライトコマンドを受領すると、ライトデータに第１データ保証コードを設定し、ライトデータに関連するパリティに第２データ保証コードを設定する。コントローラ２は、ホスト４からリードコマンドを受領すると、第１データ保証コードに基づいてデータの正誤を判定し、さらに、第１データ保証コードと第２保証コードとを比較することにより、障害の有無を検出する。障害が検出された場合、コントローラ２は、ＲＡＩＤ技術に基づいて障害を回復する。 【選択図】図１

Method for processing a cache barrier command for a disk array and device for the same

Provided is a method of controlling a RAID controller, the method including generating, by the RAID controller, a command sequence, and transmitting, by the RAID controller, when a first cache barrier command included in the command sequence is identified, at least one cache barrier command to an arbitrary disk constituting a RAID before transmitting a first write command arranged after the first cache barrier command in the command sequence to the arbitrary disk.

디스크 배열을 위한 캐시베리어 명령 처리 방법 및 이를 위한 장치