System and method for using free space to improve erasure code locality

A non-transitory computer readable medium having stored thereon instructions for causing a processing circuitry to execute a process, the process comprising:

• segmenting at least one erasure coding data set into at least one stripe based on an erasure coding scheme, wherein each erasure coding data set includes a plurality of chunks, wherein the plurality of chunks includes a plurality of chunks of systematic data and a plurality of chunks of parity data;
• wherein each chunk of the plurality of chunks of parity data is calculated by a summation function that is applied on a certain number of chunks of the plurality of chunks of systematic data, wherein the certain number is smaller than a number of a plurality of non-volatile memory nodes including the plurality of chunks of systematic data;
• distributing the at least one stripe across the plurality of non-volatile memory nodes based on the erasure coding scheme, wherein each non-volatile memory node is a unit of a non-volatile storage device;
• and
• upon a first failure of one of the non-volatile memory nodes:
• detecting that at least one of the non-volatile memory nodes that is not failed includes a first free space that does not currently store user data;
• and
• performing a first recovery process for recovering a first portion of the at least one erasure coding data set, based on the first free space.

A system using free space for recovering erasure coding data sets, comprising:

• a processing circuitry;
• and
• a memory, the memory containing instructions that, when executed by the processing circuitry, configure the system to:
• segment at least one erasure coding data set into at least one stripe based on an erasure coding scheme, wherein each erasure coding data set includes a plurality of chunks, wherein the plurality of chunks includes a plurality of chunks of systematic data and a plurality of chunks of parity data;
• wherein each chunk of the plurality of chunks of parity data is calculated by a summation function that is applied on a certain number of chunks of the plurality of chunks of systematic data, wherein the certain number is smaller than a number of a plurality of non-volatile memory nodes including the plurality of chunks of systematic data;
• distribute the at least one stripe across the plurality of non-volatile memory nodes based on the erasure coding scheme, wherein each non-volatile memory node is a unit of a non-volatile storage device;
• and
• upon a first failure of one of the non-volatile memory nodes:
• detect that at least one of the non-volatile memory nodes that is not failed includes a first free space that does not currently store user data;
• and
• perform a first recovery process for recovering a first portion of the at least one erasure coding data set, based on the first free space.