Parity logs for RAID systems with variable capacity media

Patent metadata

Field	Value
Publication number	US-9454333-B2
Application number	US-201414524829-A
Country	US
Kind code	B2
Filing date	Oct 27, 2014
Priority date	Oct 27, 2014
Publication date	Sep 27, 2016
Grant date	Sep 27, 2016

Abstract

Embodiments of the invention provide parity logs for raid systems with variable-capacity media. In one embodiment, a system includes a first set of data storage media devices having variable capacity. The storage devices include a data portion of a parity data set for storing write data being striped to the first. The system further includes a second set of data storage media devices having variable capacity. The second set includes a linear address space of blocks for storing a parity portion of the parity data set. The linear address space is written in a log form. The first and second sets comprise at least one array in a RAID configuration. The system writes the parity portion of the parity data set to the second set, which enables each storage device among the first set to be written to full capacity.

First claim

What we claim is:

1. A system, comprising:
a first set of data storage media devices having variable capacity and that comprise a data portion of a parity data set for storing write data being striped to said first set;
a second set of data storage media devices having variable capacity and a linear address space of blocks for storing a parity portion of the parity data set, said linear address space being written in a log form; and
wherein said first and second sets comprise at least one array in a RAID configuration, and writing the parity portion of the parity data set to said second set enables each data storage media device among said first set to be written to full capacity.

2. The system of claim 1 , wherein the address space is physically mapped to devices among the second set.

3. The system of claim 1 , wherein the system keeps track of log segments that correlate to said first set.

4. The system of claim 1 , wherein if said array has multiple parities, each distinct parity is written to physically separate data storage media devices among said second set.

5. The system of claim 4 , wherein each distinct parity is placed on physically separate storage media devices of the second set by using separate logs for each the data storage media devices of the first set.

6. The system of claim 1 , wherein the system demounts a data storage media device of the second set that is full and mounts an empty storage media device transparently to a writing application when writing parity for said array.

7. The system of claim 6 , wherein a different array is appended at a later time for subsequent parity writing.

8. The system of claim 1 , further comprising:
a memory device for buffering and/or staging parity data that would exceed storage capacity of a variable-capacity device among said second set if written.

9. The system of claim 8 , wherein parity data is buffered until sufficient parity data has been buffered that would fill a single storage media device among said second set and then streamed to said single device.

10. The system of claim 9 , wherein said buffering avoids capacity loss, on storage media devices among the second set, due to temperature and humidity changes caused by mounting of a same store media device for writing at different times.

11. The system of claim 1 , wherein following a loss of a data storage media device among said first set, data stored on the parity data set is recovered by reading parity information from storage media devices among the second set when the parity information for the set of devices spans multiple devices in one or more logs.

12. The system of claim 1 , wherein for stripes that need to have their strips on storage media devices that have insufficient storage capacity compared to other devices in the first set, the system uses blocks of zeros in place of such strips to compute parity of the stripe and for reconstruction of data stored in such stripes.

13. The system of claim 1 , wherein storage capacity in the second set used by the log is reclaimable.

14. The system of claim 13 , wherein the system relocates fragments of said parity portion not reclaimed to a different storage media device among said second set that does not comprise a different parity of the same array.

15. The system of claim 14 , wherein parity fragments from the array from different segments of the log are merged during reclaim process and segments are re-written to a new storage media device among second set in stripe order.

16. The system of claim 1 , wherein the storage system thereby manages capacity variation of the first set of devices and protects all of stripes in a stripe set of the array when writing the parity checks for a level of the RAID configuration by utilizing each of the first set of devices' full capacity.

17. The system of claim 1 , wherein the storage media devices among the second set are logically concatenated together.

18. A method, comprising:
storing write data being striped to a first set of data storage media devices having variable capacity and that comprise a data portion of a parity data set;
storing a parity portion of the parity data set to a second set of data storage media devices having variable capacity and a linear address space of blocks, the linear address space being written in a log form; and
wherein said first and second sets comprise at least one array in a RAID configuration, and writing the parity portion of the parity data set to said second set enables each data storage media device among said first set to be written to full capacity.

19. The method of claim 1 , wherein said writing thereby manages capacity variation of the first set of devices and protects all of stripes in a stripe set of the array when writing the parity checks for a level of the RAID configuration by utilizing each of the first set of devices' full capacity.

20. A computer program product comprising a non-transitory computer readable storage medium having computer usable program code embodied therewith, said program code being executable to:
store write data being striped to a first set of data storage media devices having variable capacity and the comprise a data portion of a parity data set;
store a parity portion of the parity data set to a second set of data storage media devices having variable capacity and a linear address space of blocks, the linear address space being written in a log form; and
wherein said first and second sets comprise at least one array in a RAID configuration, and write the parity portion of the parity data set to said second set enables each data storage media device among said first set to be written to full capacity.

Assignees

• IBM

Inventors

• Blaum Mario
• Deenadhayalan Veera W
• Hetzler Steven R
• Hineman Wayne C
• Rees Robert M
• Zhou Pin

Classifications

• G06F3/0689 Primary

  Disk arrays, e.g. RAID, JBOD · CPC title

• G06F3/0619

  in relation to data integrity, e.g. data losses, bit errors · CPC title

• G06F3/0601

  Interfaces specially adapted for storage systems · CPC title

• G06F3/0682

  Tape device · CPC title

• G06F12/0646

  Configuration or reconfiguration · CPC title