Concurrent remote IO processing for synchronous replication

Patent metadata

Field	Value
Publication number	US-10936451-B2
Application number	US-201816168910-A
Country	US
Kind code	B2
Filing date	Oct 24, 2018
Priority date	Oct 24, 2018
Publication date	Mar 2, 2021
Grant date	Mar 2, 2021

Abstract

In a data storage system in which a first storage array and a second storage array maintain first and second replicas of a production volume, the first storage array is responsive to a write command from a host to send a notification to the second storage array indicating that the replicated production volume will be updated. The notification has information that enables the second storage array to implement pre-processing steps to prepare for subsequent receipt of data associated with the write command. Both storage arrays implement the pre-processing steps at least partly concurrently. When the data associated with the write command is subsequently received, the first storage array writes the data to cache and then sends a copy of the data to the second storage array, i.e. in series. The second storage array then writes the data to cache. Elapsed time between receipt of the write command and returning an acknowledgment to the host may be improved by concurrent pre-processing.

First claim

What is claimed is:

1. An apparatus comprising:
a first storage array comprising a plurality of interconnected computing nodes, each of the computing nodes comprising at least one processor and non-transitory memory, and a plurality of groups of data storage drives, each group of data storage drives connected with one of the computing nodes, wherein the first storage array maintains a first replica of a replicated volume comprising contiguous logical block addresses that map to non-contiguous addresses of the data storage drives;
program code running on the first storage array, responsive to receipt of an IO command from a host that will update the replicated volume, which generates a notification that an IO that will update the replicated volume is impending, the notification being generated before data associated with the IO command is received by the first storage array and before the data associated with the IO command is received by the second storage array and comprising information that enables implementation of pre-processing to prepare for receipt of data associated with the impending IO, the information comprising logical block addresses that will be affected by the impending IO;
program code running on the first storage array that provides the notification to a second storage array that maintains a second replica of the replicated volume before the data associated with the IO command is received by the first storage array and before the data associated with the IO command is received by the second storage array; and
program code running on the first storage array and the second storage array that implements the pre-processing before the data associated with the IO command is received by the first storage array and before the data associated with the IO command is received by the second storage array to prepare for receipt of the data associated with the impending IO at least partly concurrently with implementation of the pre-processing by the second storage array, the pre-processing comprising locking the logical block addresses that will be affected by the impending IO.

2. The apparatus of claim 1 wherein the notification indicates at least one of: device number, cylinder number, head (track), and size.

3. The apparatus of claim 1 wherein the pre-processing comprises identifying metadata associated with the impending IO.

4. The apparatus of claim 3 wherein the pre-processing comprises using the identified metadata to identify locations in volatile memory associated with the impending IO.

5. The apparatus of claim 4 wherein the pre-processing comprises locking the identified locations.

6. The apparatus of claim 1 further comprising program code that writes the data to the memory at least partly concurrently with the second storage array writing the data to memory.

7. A method comprising:
in a network comprising:
a first storage array comprising a plurality of interconnected first computing nodes, each of the first computing nodes comprising at least one processor and non-transitory memory, and a plurality of groups of first data storage drives, each group of first data storage drives connected with one of the first computing nodes, wherein the first storage array maintains a first replica of a replicated volume comprising contiguous logical block addresses that map to non-contiguous addresses of the first data storage drives; and
a second storage array comprising a plurality of interconnected second computing nodes, each of the second computing nodes comprising at least one processor and non-transitory memory, and a plurality of groups of second data storage drives, each group of second data storage drives connected with one of the second computing nodes, wherein the second storage array maintains a second replica of the replicated volume comprising contiguous logical block addresses that map to non-contiguous addresses of the second data storage drives;
the first storage array generating a notification that an impending IO will update the replicated volume, the notification being generated before data associated with the impending IO is received by the first storage array and before the data associated with the impending IO is received by the second storage array and comprising information that enables implementation of pre-processing steps to prepare for receipt of data associated with the impending IO, the information comprising logical block addresses that will be affected by the impending IO;
the first storage array providing the notification to the second storage array before the data associated with the impending IO is received by the first storage array and before the data associated with the impending IO is received by the second storage array; and
the first storage array implementing the pre-processing steps to prepare for receipt of the data associated with the impending IO at least partly concurrently with implementation of the pre-processing steps by the second storage array and before the data associated with the impending IO is received by the first storage array and before the data associated with the impending IO is received by the second storage array, the pre-processing comprising locking the logical block addresses that will be affected by the impending IO.

8. The method of claim 7 wherein generating the notification comprises indicating at least one of: device number, cylinder number, head (track), and size.

9. The method of claim 7 wherein implementing the pre-processing steps comprises identifying metadata associated with the impending IO.

10. The method of claim 9 wherein implementing the pre-processing steps comprises using the identified metadata to identify locations in volatile memory associated with the impending IO.

11. The method of claim 10 wherein implementing the pre-processing steps comprises locking the identified locations.

12. The method of claim 7 further comprising the first storage array writing the data to the memory at least partly concurrently with the second storage array writing the data to memory.

13. A system comprising:
a first storage array comprising a plurality of interconnected first computing nodes, each of the first computing nodes comprising at least one processor and non-transitory memory, and a plurality of groups of first data storage drives, each group of first data storage drives connected with one of the first computing nodes, wherein the first storage array maintains a first replica of a replicated volume comprising contiguous logical block addresses that map to non-contiguous addresses of the first data storage drives; and
a second storage array comprising a plurality of interconnected second computing nodes, each of the second computing nodes comprising at least one processor and non-transitory memory, and a plurality of groups of second data storage drives, each group of second data storage drives connected with one of the second computing nodes, wherein the second storage array maintains a second replica of the replicated volume comprising contiguous logical block addresses that map to non-contiguous addresses of the second data storage drives;
wherein the first storage array is responsive to a write command from a host to generate a notification that the replicated volume will be updated, the notification being generated before data associated with the write command is received by the first storage array and before the data associated with the write command is received by the second storage array and comprising information that enables implementation of pre-processing steps to prepare for subsequent receipt of data associated with the write command, the information comprisin

Assignees

• Emc Ip Holding Co Llc

Inventors

• Tannous Toufic
• Bora Bhaskar
• Vokaliga Deepak

Classifications

• G06F3/065

  Replication mechanisms · CPC title

• G06F12/084

  with a shared cache · CPC title

• G06F11/2064

  while ensuring consistency · CPC title

• G06F12/126

  with special data handling, e.g. priority of data or instructions, handling errors or pinning · CPC title

• G06F11/2076

  Synchronous techniques · CPC title