Method and apparatus for asymmetric raid

• US 10,452,306 B1
• Filed: 12/31/2013
• Issued: 10/22/2019
• Est. Priority Date: 12/31/2013
• Status: Active Grant

• Current Assignee: Emc IP Holding Company LLC (Dell Technologies Inc.)
• Original Assignee: Emc IP Holding Company LLC (Dell Technologies Inc.)
• Inventors: Natanzon, Assaf, Don, Arieh, Benhanokh, Zvi Gabriel, Veprinsky, Alexandr, Bachmat, Eitan
• Primary Examiner(s): Rigol, Yaima
• Assistant Examiner(s): Waddy, Jr., Edward
• Application Number:
  US14/144,651
• Time in Patent Office: 2,121 Days
• Field of Search: 711162, 711E12001, 711E12103, 711E12008, 711117, 711154
• CPC Class Codes: G06F 3/061 Improving I/O performance
• CPC Class Codes: G06F 3/0613 in relation to throughput
• CPC Class Codes: G06F 3/0619 in relation to data integrity, e.g. data losses, bit errors
• CPC Class Codes: G06F 3/065 Replication mechanisms
• CPC Class Codes: G06F 3/0659 Command handling arrangements, e.g. command buffers, queues, command scheduling
• CPC Class Codes: G06F 3/0685 Hybrid storage combining heterogeneous device types, e.g. hierarchical storage, hybrid arrays
• CPC Class Codes: G06F 3/0689 Disk arrays, e.g. RAID, JBOD

Abstract

Example embodiments of the present invention relate to a method, an apparatus, and a computer program product for mirroring data in a data storage system across a first storage device having a first latency and a second storage device having a second latency. The method includes receiving an I/O at the data storage system and controlling the I/O to the first storage device having the first latency or the second storage device having the second latency according to properties of the I/O and properties of the first storage device having the first latency and the second storage device having the second latency.

Claims

1. A method for mirroring data in a data storage system across a first storage device having a first lower latency, lower than a second higher latency, and a second storage device having the second higher latency, the method comprising:

receiving an I/O at the data storage system; and

maintaining an I/O processing performance associated with the first storage device by controlling the I/O to the first storage device having the first lower latency and the second storage device having the second higher latency, wherein the second storage device is used as a log device, and wherein the controlling the I/O is according to properties of the I/O, properties of the first storage device having the first lower latency, and the properties of the second storage device having the second higher latency, wherein the controlling further comprising;

if the I/O is a read I/O, directing the read I/O to the first storage device having the first lower latency;

if the I/O is a write I/O,

directing the write I/O to the first storage device having the first lower latency;

directing the write I/O to the second storage device having the second higher latency as a log device sequentially as a first extent, further comprising;

receiving a plurality of write I/Os;

aggregating the write I/O with the plurality of write I/Os; and

writing the plurality of write I/Os to the second storage device having the second higher latency as the log device; and

storing on a third storage device a mapping between a first offset for the first storage device having the first lower latency, and a second offset for the second storage device having the second higher latency.

2. The method of claim 1 wherein writing the plurality of write I/Os sequentially to the second storage device having the second higher latency as the log device comprises:

writing the plurality of write I/Os sequentially to the second storage device having the second higher latency as the first extent; and

maintaining a respective pointer on the third storage device having a third lower latency identifying a storage location on the second storage device having the second higher latency of data written from each of the plurality of write I/Os.

3. The method of claim 2 wherein writing the plurality of write I/Os sequentially to the second storage device having the second higher latency as the log device comprises:

allocating a first lesser amount of storage, less than a second greater amount of storage, on the first storage device having the first lower latency;

allocating the second greater amount of storage on the second storage device having the second higher latency; and

freeing storage on the second storage device used as the log device having the second higher latency.

4. The method of claim 3 wherein freeing storage on the second storage device used as the log device having the second higher latency comprises:

reading data from the first extent that is not full on the second storage device used as the log device having the second higher latency,

reading data from a second extent that is not full on the second storage device used as the log device having the second higher latency; and

writing a third extent that is full to the second storage device used as the log device having the second higher latency comprising the data from the first extent and the data from the second extent.

5. The method of claim 1 wherein the second storage device having a second higher latency is a first Redundant Array of Independent Disks (RAID) cloud storage device comprising a plurality of storage devices having the second latency.

6. The method of claim 5 wherein controlling I/Os to the data storage system according to properties of the I/O and properties of the first storage device and properties of the second storage device comprises:

detecting a failure of the first storage device having the first latency;

directing I/Os intended for the failed first storage device having the first latency to the first RAID cloud storage device having the second latency; and

replacing the failed first storage device having the first latency.

7. The method of claim 5 wherein the first storage device having the first latency is a second RAID cloud storage device comprising a plurality of first storage devices having the first latency.

8. The method of claim 7 wherein controlling I/Os to the data storage system according to properties of the I/O and properties of the first storage device and properties of the second storage device comprises:

detecting a failure of a particular first storage device having the first latency of the second RAID cloud storage device;

directing I/Os intended for the failed particular first storage device to the second RAID cloud storage device having the second latency, and

replacing the failed particular first storage device having the first latency of the second RAID cloud storage device.

9. A data storage system comprising:

a first storage device having a first lower latency, lower than a second higher latency;

a second storage device having the second higher latency, wherein the second storage device is used as a log device;

a third storage device having a mapping between a first offset for the first storage device having the first lower latency, and a second offset for the second storage device having the second high latency; and

a controller configured for;

receiving an I/O at the data storage system; and

maintaining an I/O processing performance associated with the first storage device by controlling the I/O to the first storage device having the first lower latency and the second storage device having the second higher latency, wherein the controlling the I/O is according to properties of the I/O, properties of the first storage device having the first lower latency, and the properties of the second storage device having the second higher latency, wherein the controlling further comprising;

if the I/O is a read I/O, directing the read I/O to the first storage device having the first lower latency;

if the I/O is a write I/O,

directing the write I/O to the first storage device having the first lower latency;

directing the write I/O to the second storage device having the second higher latency as a log device sequentially as a first extent, further comprising;

receiving a plurality of write I/Os;

aggregating the write I/O with the plurality of write I/Os; and

writing the plurality of write I/Os to the second storage device having the second higher latency as the log device; and

storing on a third storage device a mapping between a first offset for the first storage device having the first lower latency, and a second offset for the second storage device having the second higher latency.

10. The system of claim 9 wherein the controller is further configured to write the plurality of write I/Os sequentially to the second storage device having the second higher latency as the first extent and maintain a respective pointer on the third storage device having a third lower latency identifying a storage location on the second storage device having the second higher latency of data written from each of the plurality of write I/Os.

11. The system of claim 10 wherein the controller is further configured to allocate a first lesser amount of storage, less than a second greater amount of storage, on the first storage device having the first lower latency, allocate the second greater amount of storage on the second storage device having the second higher latency, and free storage on the second storage device used as the log device having the second higher latency.

12. The system of claim 11 wherein the controller is further configured to read data from the first extent that is not full on the second storage device used as the log device having the second higher latency, read data from a second extent that is not full on the second storage device used as the log device having the second higher latency, and write a third extent that is full to the second storage device used as the log device having the second higher latency comprising the data from the first extent and the data from the second extent.

13. The system of claim 9 wherein the second storage device having a second higher latency is a first Redundant Array of Independent Disks (RAID) cloud storage device comprising a plurality of storage devices having the second latency.

14. The system of claim 13 wherein the controller is further configured to detect a failure of the first storage device having the first latency, direct I/Os intended for the failed first storage device having the first latency to the first RAID cloud storage device having the second latency, and replace the failed first storage device having the first latency.

15. The system of claim 13 wherein the first storage device having the first latency is a second RAID cloud storage device comprising a plurality of first storage devices having the first latency.

16. The system of claim 15 wherein the controller is further configured to detect a failure of a particular first storage device having the first latency of the second RAID cloud storage device, direct I/Os intended for the failed particular first storage device to the second RAID cloud storage device having the second latency, and replace the failed particular first storage device having the first latency of the second RAID cloud storage device.

17. A computer program product including a non-transitory computer readable storage medium having computer program code encoded thereon that, when executed on one or more processors of a computer system, causes the computer system to mirror data in a data storage system across a first storage device having a first lower latency, lower than a second higher latency, and a second storage device having the second higher latency, the computer program product comprising program code of one or more software programs, wherein the program code when executed by at least one processing device causes the at least one processing device to:

receive an I/O at the data storage system; and

maintain an I/O processing performance associated with the first storage device by controlling the I/O to the first storage device having the first lower latency and the second storage device having the second higher latency, wherein the second storage device is used as a log device, and wherein the controlling the I/O is according to properties of the I/O, properties of the first storage device having the first lower latency, and the properties of the second storage device having the second higher latency, wherein the controlling further comprising;

if the I/O is a read I/O, direct the read I/O to the first storage device having the first lower latency;

if the I/O is a write I/O,

direct the write I/O to the first storage device having the first lower latency;

direct the write I/O to the second storage device having the second higher latency as a log device sequentially as a first extent, further comprising;

receive a plurality of write I/Os;

aggregate the write I/O with the plurality of write I/Os; and

write the plurality of write I/Os to the second storage device having the second higher latency as the log device; and

store on a third storage device a mapping between a first offset for the first storage device having the first lower latency, and a second offset for the second storage device having the second higher latency.