Alignment fixing on a data protection system during continuous data replication to deduplicated storage

• US 9,772,789 B1
• Filed: 03/25/2014
• Issued: 09/26/2017
• Est. Priority Date: 03/25/2014
• 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, Cohen, Saar, Panidis, Anestis
• Primary Examiner(s): Schnee, Hal
• Application Number:
  US14/225,104
• Time in Patent Office: 1,281 Days
• CPC Class Codes: G06F 11/1453 using de-duplication of the data
• CPC Class Codes: G06F 11/1471 involving logging of persistent data for recovery
• CPC Class Codes: G06F 11/1474 in transactions G06F16/20 takes precedence
• CPC Class Codes: G06F 11/2094 Redundant storage or storage space G06F11/2056 takes precedence
• CPC Class Codes: G06F 11/2097 maintaining the standby controller/processing unit updated initialisation or re-synchronisation thereof G06F11/1658 and subgroups
• CPC Class Codes: G06F 2201/84 Using snapshots, i.e. a logical point-in-time copy of the data
• CPC Class Codes: G06F 3/0608 Saving storage space on storage systems
• CPC Class Codes: G06F 3/0641 De-duplication techniques
• CPC Class Codes: G06F 3/065 Replication mechanisms
• CPC Class Codes: G06F 3/067 Distributed or networked storage systems, e.g. storage area networks [SAN], network attached storage [NAS]

Abstract

The system, process, and methods herein describe a mechanism for aligning IOs with block sizes. The alignment may occur on a data protection appliance as part of a continuous replication process. The IO offset may be rounded down, and the size may be rounded up, so that each is a multiple of the block size.

Claims

1. A method for IO alignment, comprising:

receiving an IO comprising a write to a storage device, wherein the IO includes data journal entries to store on a journal data file and metadata entries to store on a metadata journal file on a deduplicated storage;

determining that the data journal entries in the IO are not aligned with a storage block on the deduplicated storage;

aligning the IO with the storage block after determining that the IO and the storage block are not aligned by providing a primary storage offset for the IO that aligns the IO with the storage block;

writing the data journal entries to the storage block in the journal data file;

storing the primary storage offset in the metadata journal file apart from the data journal entries in the journal data file; and

synthesizing backup snapshots that include pointers to the data journal entries in prior snapshots and the data journal entries representing changes to the data journal entries in the prior snapshots after the prior snapshots were synthesized;

wherein the aligning of the IO prevents data journal entries movements during synthesizing of the backup snapshots and the backup snapshots are logical units identified by logical unit numbers on the deduplicated storage.

2. The method of claim 1, further comprising:

determining a block size for the storage block; and

determining the primary storage offset from an IO size and the block size for the storage block.

3. The method of claim 2, further comprising determining the IO is not aligned with the storage block when the IO offset is not a multiple of the block size.

4. The method of claim 3, further comprising rounding the IO offset down to a start offset, wherein the start offset is a multiple of the block size.

5. The method of claim 4, further comprising padding a difference between the start offset and the IO offset.

6. The method of claim 4, further comprising sending a read request to the storage device, the read request comprising a request for data at the start offset.

7. The method of claim 4, wherein the start offset is a nearest lower offset that is a multiple of the block size.

8. The method of claim 2, further comprising determining the IO is not aligned with the storage block when the IO size is not a multiple of the block size.

9. The method of claim 8, further comprising padding the IO to a new IO size, wherein the new IO size is a multiple of the block size.

10. The method of claim 9, further comprising sending a read request to the storage device, the read request comprising a request for data on the storage device within the new IO size.

11. The method of claim 1, further comprising tracking the IO when it is not aligned with the storage block.

12. The method of claim 11, further comprising waiting for a host to flush an open IO to the storage device.

13. The method of claim 12, further comprising sending a read request to the storage device.

14. The method of claim 13, further comprising receiving a second IO from the host.

15. The method of claim 14, further comprising determining whether the second IO comprises a write to a read data requested by the read request.

16. A computer program product for alignment, the computer program product comprising a non-transitory computer readable medium encoded with computer executable program, the code enabling:

receiving an IO comprising a write to a storage device, wherein the IO includes data journal entries to store on a journal data file and metadata entries to store on a metadata journal file on a deduplicated storage;

determining that the data journal entries in the IO are not aligned with a storage block on the deduplicated storage;

aligning the IO with the storage block after determining that the IO and the storage block are not aligned by providing a primary storage offset for the IO that aligns the IO with the storage block;

writing the data journal entries to the storage block in the journal data file;

storing the primary storage offset in the metadata journal file apart from the data journal entries in the journal data file; and

synthesizing backup snapshots that include pointers to the data journal entries in prior snapshots and the data journal entries representing changes to the data journal entries in the prior snapshots after the prior snapshots were synthesized;

wherein the aligning of the IO prevents data journal entries movements during synthesizing of the backup snapshots and the backup snapshots are logical units identified by logical unit numbers on the deduplicated storage.

17. A system for alignment comprising a memory and a processor, the processor configured to execute instructions comprising:

receiving an IO comprising a write to a storage device, wherein the IO includes data journal entries to store on a journal data file and metadata entries to store on a metadata journal file on a deduplicated storage;

determining that the data journal entries in the IO are not aligned with a storage block on the deduplicated storage;

aligning the IO with the storage block after determining that the IO and the storage block are not aligned by providing a primary storage offset for the IO that aligns the IO with the storage block;

writing the data journal entries to the storage block in the journal data file;

storing the primary storage offset in the metadata journal file apart from the data journal entries in the journal data file; and

synthesizing backup snapshots that include pointers to the data journal entries in prior snapshots and the data journal entries representing changes to the data journal entries in the prior snapshots after the prior snapshots were synthesized;

wherein the aligning of the IO prevents data journal entries movements during synthesizing of the backup snapshots and the backup snapshots are logical units identified by logical unit numbers on the deduplicated storage.