Method and system for facilitating low-cost high-throughput storage for accessing large-size I/O blocks in a hard disk drive

1. A computer-implemented method, comprising:

receiving a first request to write data to a hard disk drive (HDD) which comprises a plurality of platters with corresponding heads, wherein a respective platter includes a plurality of tracks;

aligning the heads at a same first position on a first track of each platter;

writing the data to the platters by distributing the data as a plurality of data sectors to track sectors located at the same first position on the first track of each platter;

receiving a second request to read the data from the HDD;

identifying the first track as a location at which the data is stored;

aligning the heads at a same random position on the first track of each platter;

reading, during a single rotation of the platters and beginning from the same random position, all data stored on the first track of each platter;

storing the read data in a data buffer; and

reshuffling the read data in the data buffer to obtain the data requested in the second request.

2. The method of claim 1 , further comprising:

receiving a third request to read the data from the hard disk drive, wherein the data requested in the third request is stored in the first track of each platter;

determining that the data requested in the third request is stored in the data buffer;

retrieving the data requested in the third request from the data buffer without reading the data stored in the first track of each platter; and

returning the retrieved data.

3. The method of claim 1 ,

wherein aligning the heads at the same first position or the same random position comprises activating a plurality of arms associated with the plurality of platters of the hard disk drive, wherein a respective arm is attached to a corresponding head of a respective platter, and

wherein writing the data to the platters by distributing the data as a plurality of data sectors is based on a logical block address associated with a respective data sector.

4. The method of claim 1 , wherein a respective track includes a plurality of pre-allocated spare sectors for remapping data stored in a faulty sector of the respective track.

5. The method of claim 1 ,

wherein the data buffer is maintained by the hard disk drive or a host; and

wherein reshuffling the read data in the data buffer is performed by the hard disk drive or the host.

6. The method of claim 1 , further comprising:

writing replicas of the data to other hard disk drives of a distributed storage system,

wherein the replicas are written by distributing a respective replica as a plurality of data sectors to track sectors located at a same second position on a second track of each platter of a respective other hard disk drive;

receiving a third request to read the data stored in the distributed storage system;

obtaining a unique portion of the data requested in the third request from each of the hard disk drives on which the data or replicas of the data are stored;

concatenating the unique portions in a correct order to form the data requested in the third request; and

returning the concatenated data in response to the third request.

7. The method of claim 6 ,

wherein the unique portion of the data obtained from each of the hard disk drives is determined by a file system of the distributed storage system, and

wherein the concatenation of each unique portion comprises an entirety of the data requested in the third request.

8. A computer system, comprising:

a processor; and

a memory coupled to the processor and storing instructions which, when executed by the processor, cause the processor to perform a method, the method comprising:

receiving a first request to write data to a hard disk drive (HDD) which comprises a plurality of platters with corresponding heads, wherein a respective platter includes a plurality of tracks;

aligning the heads at a same first position on a first track of each platter;

writing the data to the platters by distributing the data as a plurality of data sectors to track sectors located at the same first position on the first track of each platter;

receiving a second request to read the data from the HDD;

identifying the first track as a location at which the data is stored;

aligning the heads at a same random position on the first track of each platter;

reading, during a single rotation of the platters and beginning from the same random position, all data stored on the first track of each platter;

storing the read data in a data buffer; and

reshuffling the read data in the data buffer to obtain the data requested in the second request.

9. The computer system of claim 8 , wherein the method further comprises:

receiving a third request to read the data from the hard disk drive, wherein the data requested in the third request is stored in the first track of each platter;

determining that the data requested in the third request is stored in the data buffer;

retrieving the data requested in the third request from the data buffer without reading the data stored in the first track of each platter; and

returning the retrieved data.

10. The computer system of claim 8 ,

wherein aligning the heads at the same first position or the same random position comprises activating a plurality of arms associated with the plurality of platters of the hard disk drive, wherein a respective arm is attached to a corresponding head of a respective platter, and

wherein writing the data to the platters by distributing the data as a plurality of data sectors is based on a logical block address associated with a respective data sector.

11. The computer system of claim 8 , wherein a respective track includes a plurality of pre-allocated spare sectors for remapping data stored in a faulty sector of the respective track.

12. The computer system of claim 8 ,

wherein the data buffer is maintained by the hard disk drive or a host; and

wherein reshuffling the read data in the data buffer is performed by the hard disk drive or the host.

13. The computer system of claim 8 , wherein the method further comprises:

writing replicas of the data to other hard disk drives of a distributed storage system,

wherein the replicas are written by distributing a respective replica as a plurality of data sectors to track sectors located at a same second position on a second track of each platter of a respective other hard disk drive;

receiving a third request to read the data stored in the distributed storage system;

obtaining a unique portion of the data requested in the third request from each of the hard disk drives on which the data or replicas of the data are stored;

concatenating the unique portions in a correct order to form the data requested in the third request; and

returning the concatenated data in response to the third request.

14. The computer system of claim 13 ,

wherein the unique portion of the data obtained from each of the hard disk drives is determined by a file system of the distributed storage system, and

wherein the concatenation of each unique portion comprises an entirety of the data requested in the third request.

15. An apparatus, comprising:

a non-volatile memory of a hard disk drive,

wherein the hard disk drive comprises a plurality of platters with corresponding heads, wherein a respective platter includes a plurality of tracks; and

a controller configured to:

receive a first request to write data to the hard disk drive;

align the heads at a same first position on a first track of each platter; and

write the data to the platters by distributing the data as a plurality of data sectors to track sectors located at the same first position on the first track of each platter;

receive a second request to read the data from the HDD;

identify the first track as a location at which the data is stored;

align the heads at a same random position on the first track of each platter;

read, during a single rotation of the platters and beginning from the same random position, all data stored on the first track of each platter;

store the read data in a data buffer; and

reshuffle the read data in the data buffer to obtain the data requested in the second request.

16. The apparatus of claim 15 , wherein the controller is further configured to:

receive a third request to read the data from the hard disk drive, wherein the data requested in the third request is stored in the first track of each platter;

determine that the data requested in the third request is stored in the data buffer;

retrieve the data requested in the third request from the data buffer without reading the data stored in the first track of each platter; and

return the retrieved data.

17. The apparatus of claim 15 ,

wherein a respective track includes a plurality of pre-allocated spare sectors for remapping data stored in a faulty sector of the respective track,

wherein aligning the heads at the same first position or the same random position comprises activating a plurality of arms associated with the plurality of platters of the hard disk drive, wherein a respective arm is attached to a corresponding head of a respective platter, and

wherein writing the data to the platters by distributing the data as a plurality of data sectors is based on a logical block address associated with a respective data sector.