摘要:
In the storage-based snapshot creation, a block-selection specifying unit provided on a NAS processing unit specifies a block, which becomes necessary for the generation of snapshot data, to a specified-block analyzing unit within a disk apparatus. Moreover, a disk controller generates the snapshot data on the block specified as the snapshot target, while making an inquiry to the specified-block analyzing unit. This makes it possible to create the snapshot in a storage-capacity reduced manner, and to specify the snapshot creation in a partition, file, or directory unit.
摘要:
In the storage-based snapshot creation, a block-selection specifying unit provided on a NAS processing unit specifies a block, which becomes necessary for the generation of snapshot data, to a specified-block analyzing unit within a disk apparatus. Moreover, a disk controller generates the snapshot data on the block specified as the snapshot target, while making an inquiry to the specified-block analyzing unit. This makes it possible to create the snapshot in a storage-capacity reduced manner, and to specify the snapshot creation in a partition, file, or directory unit.
摘要:
In the storage-based snapshot creation, a block-selection specifying unit provided on a NAS processing unit specifies a block, which becomes necessary for the generation of snapshot data, to a specified-block analyzing unit within a disk apparatus. Moreover, a disk controller generates the snapshot data on the block specified as the snapshot target, while making an inquiry to the specified-block analyzing unit. This makes it possible to create the snapshot in a storage-capacity reduced manner, and to specify the snapshot creation in a partition, file, or directory unit.
摘要:
A file server has plural NAS nodes having three processors dispersed in function, a shared cache memory shared between the plural NAS nodes and backed up by a battery, and plural storage devices. A log area for storing data with respect to an access request received by each NAS node is arranged in the shared cache memory. A network processor stores the data with respect to the access request to the log area, and transfers the data of the memory by a DMA at a reading time. Even when a failure is happened in a certain NAS node, another NAS node restores a file system using the log and continues processing to store the data with respect to the access request to the shared cache memory.
摘要:
In a storage system with a server apparatus having at least one CPU, a memory, at least one network interface, and at least one storage interface, and, at least one disk connected to the storage interface, the server apparatus has a snapshot management part which maintains and manages snapshot of the disk apparatus, the disk apparatus has an operational volume which performs ordinary read/write and a differential volume which stores differential data of snapshot of the operational volume, the snapshot management part stores data on the operational volume in the differential volume, provides a preceding copy area to store its location information, and when free area on the differential volume becomes insufficient discards the stored location information and uses the preceding copy area as an free area.
摘要:
In a storage system with a server apparatus having at least one CPU, a memory, at least one network interface, and at least one storage interface, and, at least one disk connected to the storage interface, the server apparatus has a snapshot management part which maintains and manages snapshot of the disk apparatus, the disk apparatus has an operational volume which performs ordinary read/write and a differential volume which stores differential data of snapshot of the operational volume, the snapshot management part stores data on the operational volume in the differential volume, provides a preceding copy area to store its location information, and when free area on the differential volume becomes insufficient discards the stored location information and uses the preceding copy area as an free area.
摘要:
The invention provides both interfaces of SAN and NAS, prevents data miss even when a trouble occurs and makes it possible that an arbitrary number of NAS interfaces access the same file system with high performance. A storage system includes multiple interfaces for external connection, multiple disks accessed from multiple interfaces, and a shared memory accessed from multiple interfaces. The multiple interfaces are block interfaces executing disk block I/O request, and file interfaces of file servers executing file I/O request. A file system in the file servers is constructed in a part of the disks, and a log storage area holding change log of the file system, and a management file server information storage area holding information of managing file server performing exclusive access control of file system and management of log storage area are formed in the shared memory.
摘要:
Interfaces of SAN and NAS, prevents data miss even when a trouble occurs and makes it possible that an arbitrary number of NAS interfaces access the same file system with high performance. A storage system includes multiple interfaces for external connection, multiple disks accessed from multiple interfaces, and a shared memory accessed from multiple interfaces. The multiple interfaces are block interfaces executing disk block I/O request, and file interfaces of file servers executing file I/O request. A file system in the file servers is constructed in a part of the disks, and a log storage area holding change log of the file system, and a management file server information storage area holding information of managing file server performing exclusive access control of file system and management of log storage area are formed in the shared memory.
摘要:
Interfaces of SAN and NAS, prevents data miss even when a trouble occurs and makes it possible that an arbitrary number of NAS interfaces access the same file system with high performance. A storage system includes multiple interfaces for external connection, multiple disks accessed from multiple interfaces, and a shared memory accessed from multiple interfaces. The multiple interfaces are block interfaces executing disk block I/O request, and file interfaces of file servers executing file I/O request. A file system in the file servers is constructed in a part of the disks, and a log storage area holding change log of the file system, and a management file server information storage area holding information of managing file server performing exclusive access control of file system and management of log storage area are formed in the shared memory.
摘要:
The object of the present invention is to improve an access efficiency in a distributed environment. When a user “foo” access a file “file_1a” stored in a storage node SN1 under the control of a control node CN1 from a client CLN3 via a control node CN3 as shown by the solid lien arrow in the figure, a record of the access is accumulated in an access history of the control node CN1. If the control node CN1 refers to the access history and detects the frequent accesses from the control node CN3, it replicates or migrates the file “file_1a” to a storage node SN3 controlled by the control node CN3 as shown by the bold line arrow. The replication is performed if another device has accessed the file. Otherwise the migration is performed.