Block based access to a dispersed data storage network
View Patent ↗A block-based interface to a dispersed data storage network is disclosed. The disclosed interface accepts read and write commands from a file system resident on a user's computer and generates network commands that are forwarded to slice servers that form the storage component of the dispersed data storage network. The slice servers then fulfill the read and write commands.
1. A method of reading data from a dispersed data network, said method operating on at least one computer and comprising the steps of:
identifying a data segment that includes a plurality of blocks of data, wherein the plurality of blocks of data is encoded using an information dispersal algorithm to produce a plurality of “n” number of data slices, wherein one of the plurality of blocks of data is encoded into one of the plurality of “n” number of data slices, and wherein data slices of the plurality of “n” number of data slices are grouped to produce “n” number of data slice groups which is stored in the dispersed data network, and wherein the data segment is divided into the plurality of blocks of data in accordance with the block-based file system;
assembling a list of slice servers, wherein each slice server on said list stores one of the “n” number of data slice groups;
issuing read requests for at least “m” number of data slice groups to at least “m” number of the slice servers of the list of slice servers, wherein “m” is less than “n” and represents a minimum number of data slices to recover the one of the plurality of blocks of data from the one of the plurality of “n” number of data slices;
when at least “m” number of data slice groups have been received from the at least “m” number of slice servers:
decoding the at least “m” number of data slice groups in accordance with the information dispersal algorithm to reproduce the plurality of blocks of data; and
reconstructing the data segment from the reproduced plurality of blocks of data.
2. The method of claim 1 , wherein said one of the plurality of blocks of data is encrypted and further comprising the step of decrypting said one of the plurality of blocks of data.
3. The method of claim 1 , further comprising the steps of calculating a first checksum for said one of the plurality of blocks of data, and comparing said first checksum to a second checksum appended to said one of the plurality of blocks of data.
4. The method of claim 1 , further comprising the steps of calculating a first checksum for a received data slice, and comparing said first checksum to a second checksum appended to said received data slice.
5. The method of claim 1 , wherein the block-based file system comprises at least one of:
an iSCSI protocol;
an FCP protocol; and
an ATA protocol.
6. A computer comprising:
a network interface for interfacing with a dispersed data storage network; and
a software component operable to:
receive a request for a data segment that includes a plurality of blocks of data, wherein the plurality of blocks of data is encoded using an information dispersal algorithm to produce a plurality of “n” number of data slices, wherein one of the plurality of blocks of data is encoded into one of the plurality of “n” number of data slices, and wherein data slices of the plurality of “n” number of data slices are grouped to produce “n” number of data slice groups which is stored in the dispersed data network and wherein the data segment is divided into the plurality of blocks of data in accordance with the block-based file system;
assemble a list of slice servers, wherein each slice server on said list stores one of the “n” number of data slice groups;
issue, via the network interface, read requests for at least “m” number of data slice groups to at least “m” number of the slice servers of the list of slice servers, wherein “m” is less than “n” and represents a minimum number of data slices to recover the one of the plurality of blocks of data from the one of the plurality of “n” number of data slices;
when at least “m” number of data slice groups have been received from the at least “m” number of slice servers:
decode the at least “m” number of data slice groups in accordance with the information dispersal algorithm to reproduce the plurality of blocks of data; and
reconstruct the data segment from the reproduced plurality of blocks of data.
7. The computer of claim 6 , wherein said software component is implemented as an iSCSI target.
8. The computer of claim 7 , wherein the decoding the at least “m” number of data slice groups further comprises at least one of:
applying a first data transformation on data slices of the at least “m” number of data slices groups to produce a plurality of at least “m” number of data slices;
applying the information dispersal algorithm on the plurality of at least “m” number of data slices to produce recovered plurality of data blocks; and
applying a second data transformation on the recovered plurality of data blocks to produce the reproduced plurality of blocks of data.
9. The computer of claim 6 , wherein said software component is implemented as a device driver.
10. The computer of claim 9 , wherein the block-based file system comprises at least one of:
an iSCSI protocol;
an FCP protocol; and
an ATA protocol.