Method and Apparatus for Transmitting Data Processing Request

Abstract

A just a bunch of flash solid-state drive cluster (JBOF) and a method for transmitting a data processing request include obtaining a data processing request sent by a storage controller, determining a type of the data processing request, and either forwarding the data processing request to the target solid state drive (SSD) when the type of the data processing request is a bypass type, or sending the data processing request to a computing unit in the JBOF and sending the data processing request processed by the computing unit to the target SSD when the type of the data processing request is a background computing type.

1 . A method for transmitting a data processing request, implemented by a just a bunch of flash (JBOF), and comprising:
 obtaining, by a computing unit of the JBOF, the data processing request, wherein the data processing request comprises data to be stored in a solid-state drive (SSD) in the JBOF;   implementing, by the computing unit, an erasure coding (EC) operation to the data to obtain EC data;   sending, by the computing unit, the EC data to target SSDs in the JBOF;   storing, by the target SSDs, the EC data.   
     
     
         2 . The method of  claim 1 , wherein the EC data comprises n data blocks and m parity blocks, wherein the m parity blocks are based on the n data blocks, and wherein n and m are integers. 
     
     
         3 . The method of  claim 1 , further comprising selecting, by the computing unit, the target SSDs for the n data blocks and the m parity blocks. 
     
     
         4 . The method of  claim 1 , further comprising:
 receiving, by the computing unit, a garbage collection (GC) request;   implementing, by the computing unit, a garbage collection (GC) operation on the SSD according to the GC request.   
     
     
         5 . The method of  claim 1 , wherein the computing unit is a system on chip (SoC). 
     
     
         6 . A just a bunch of flash (JBOF), comprising
 solid-state drives (SSDs), and   a processor coupled to the SSDs and configured to:
 obtain a data processing request, wherein the data processing request carries data to be stored in SSD in the JBOF; 
 implement an erasure coding (EC) operation to the data carried in the data processing request to get EC data; 
 send the EC data to target SSDs in the JBOF; 
 store the EC data in the target SSDs. 
   
     
     
         7 . The JBOF of  claim 6 , wherein the EC data comprises n data blocks and m parity blocks, wherein the m parity blocks are based on the n data blocks, and wherein n and m are integers. 
     
     
         8 . The JBOF of  claim 6 , wherein the processor is further configured to select the target SSDs for the n data blocks and the m parity blocks. 
     
     
         9 . The JBOF of  claim 6 , wherein the processor is further configured to:
 receive a garbage collection (GC) request;   implement a GC operation on a plurality of SSDs of the JBOF according to the GC request.   
     
     
         10 . The JBOF of  claim 6 , wherein the processor is a system on chip (SoC). 
     
     
         11 . The JBOF of  claim 6 , wherein the processor is further configured to determine a type of the data processing request, and wherein the type of the data processing request comprises a background computing type or a bypass type. 
     
     
         12 . The JBOF of  claim 6 , wherein each of the SSDs is a non-volatile memory express (NVMe) SSD or a serial advanced technology attachment (SATA) SSD. 
     
     
         13 . The method of  claim 1 , further comprising determining, by the computing unit, a type of the data processing request, and wherein the type of the data processing request comprises a background computing type or a bypass type. 
     
     
         14 . The method of  claim 1 , wherein each of the SSDs is a non-volatile memory express (NVMe) SSD or a serial advanced technology attachment (SATA) SSD. 
     
     
         15 . A computer program product comprising computer-executable instructions that are stored on a non-transitory computer-readable storage medium and that, when executed by a processor, cause a just a bunch of flash (JBOF) to:
 obtain a data processing request, wherein the data processing request carries data to be stored in an SSD in JBOF;   implement an erasure coding (EC) operation to the data carried in the data processing request to get EC data;   send the EC data to target SSDs in the JBOF;   storing the EC data in the target SSDs.   
     
     
         16 . The computer program product of  claim 15 , wherein the EC data comprises n data blocks and m parity blocks, wherein the m parity blocks are based on the n data blocks, and wherein n and m are integers. 
     
     
         17 . The computer program product of  claim 15 , wherein the computer-executable instructions further cause the JBOF to be configured to select the target SSDs for the n data blocks and the m parity blocks. 
     
     
         18 . The computer program product of  claim 15 , wherein the computer-executable instructions further cause the JBOF to be configured to:
 receive a garbage collection (GC) request;   implement a GC operation on the plurality of SSDs according to the GC request.   
     
     
         19 . The computer program product of  claim 15 , wherein the processor is a system on chip (SoC). 
     
     
         20 . The computer program product of  claim 15 , wherein the computer-executable instructions further cause the JBOF to be configured to determine a type of the data processing request, and wherein the type of the data processing request comprises a background computing type or a bypass type.