Distributed storage method, apparatus, and system for reducing a data loss that may result from a single-point failure

A distributed storage system, comprising:

• a client;
• multiple physical storage nodes;
• and
• a distributed storage apparatus, wherein the distributed storage apparatus stores or reads a data file of a user onto or from the multiple physical storage nodes according to a storage or read request sent by the user through the client, and wherein the distributed storage apparatus comprises:
• a generating module configured to:
• split a data file to generate K data slices;
• split each data slice of the K data slices to generate M data blocks for each data slice;
• and
• perform check coding on the M data blocks by using a redundancy algorithm to generate N check blocks;
• a determining module configured to:
• determine, by using a random algorithm, a first physical storage node corresponding to one data block or one check block of the M data blocks or the N check blocks;
• and
• determine at least M+1 different physical storage nodes based on the first physical storage node and according to a first sorting manner that conforms to a preset rule;
• and
• a storing module configured to store at least M+1 blocks of the M data blocks and the N check blocks onto the at least M+1 different physical storage nodes, wherein K, M, and N are positive integers.

A distributed storage apparatus, a processor and a memory coupled to the processor, wherein the processor is configured to:

• split a data file to generate K data slices;
• split each data slice of the K data slices to generate M data blocks for each data slice;
• perform check coding on the M data blocks by using a redundancy algorithm to generate N check blocks;
• determine by using a random algorithm, a first physical storage node corresponding to one data block or one check block of the M data blocks or the N check blocks;
• determine at least M+1 different physical storage nodes based on the first physical storage node and according to a first sorting manner that conforms to a preset rule;
• and
• separately store at least M+1 blocks of the M data blocks and the N check blocks onto the at least M+1 different physical storage nodes, wherein K, M, and N are positive integers.

A non-transitory computer-readable medium having computer executable instructions for performing an information publishing method comprising:

• Splitting a data file to generate K data slices;
• Splitting each data slice of the K data slices to generate M data blocks for each data slice;
• performing check coding on the M data blocks by using a redundancy algorithm to generate N check blocks;
• determining, by using a random algorithm, a first physical storage node corresponding to one data block or one check block of the M data blocks or the N check blocks;
• determining at least M+1 different physical storage nodes based on the first physical storage node and according to a first sorting manner that conforms to a preset rule;
• and
• separately storing at least M+1 blocks of the M data blocks and the N check blocks onto the at least M+1 different physical storage nodes, wherein K, M, and N are positive integers.