Journal destage relay for online system checkpoint creation

• US 10,235,066 B1
• Filed: 04/27/2017
• Issued: 03/19/2019
• Est. Priority Date: 04/27/2017
• Status: Active Grant

• Current Assignee: Emc IP Holding Company LLC (Dell Technologies Inc.)
• Original Assignee: Emc IP Holding Company LLC (Dell Technologies Inc.)
• Inventors: Chen, Xiangping, Kucherov, Anton, Hu, Ying, Shvaiger, Felix
• Primary Examiner(s): Ruiz, Aracelis
• Application Number:
  US15/499,293
• Time in Patent Office: 691 Days
• CPC Class Codes: G06F 12/10 Address translation
• CPC Class Codes: G06F 2212/65 Details of virtual memory and virtual address translation
• 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 3/067 Distributed or networked storage systems, e.g. storage area networks [SAN], network attached storage [NAS]

Abstract

A storage system comprising a processor in operable communication with a storage device is configured to have first, second, and third tables and first, second, and third respective metadata journals storing time-based information associated, respectively, with the first, second, and third tables. The first table maps logical addresses associated with LUNs associated with the storage device to respective hash digests computed based on data residing at respective logical addresses. The second table maps a range of hash digests to respective associated physical locations on the storage device. The third table maps disk block allocation on the storage device. An online system checkpoint is created, comprising information relating to the state of the storage system at a point in time, where the first, second, and third, metadata journals are destaged in order so as to destage information stored in the respective journal up to the point in time.

Claims

1. A computer-implemented method, comprising

configuring a storage system comprising a processor in operable communication with a storage device, the storage system responsive to input/output (I/O) requests to the storage device from a host in operable communication with the storage system;

configuring on the storage system first, second, and third tables and first, second, and third respective metadata journals associated with the first, second, and third, tables, each respective metadata journal configured to store respective contents, wherein;

the first table maps a first respective logical address associated with a first respective logical unit number (LUN) associated with the storage device to a corresponding first respective hash digest, the first respective hash digest computed based at least in part on data that resides at the first respective logical address;

the first metadata journal comprises first metadata configured to store information associated with time-based changes to information stored in the first table;

the second table maps a first range of respective hash digests to respective associated physical locations on the storage device;

the second metadata journal comprises second metadata configured to store information associated with time-based changes to information stored in the second table;

the third table comprises a mapping indicative of whether or not a given disk block on the storage device is allocated; and

the third respective metadata journal comprises third metadata configured to store information associated with time-based changes to information stored in the third table; and

creating, while the storage system is online and responsive to I/O requests from the host, an online system checkpoint comprising information relating to a state of the storage system at a first point in time, the creation of the checkpoint comprising;

creating a plurality of consistent snapshots of the storage system at the first point in time; and

destaging, in order, the first metadata journal, the second metadata journal, and the third metadata journal, wherein each destaging is configured to destage information stored in the journal up to the first point in time.

2. The computer-implemented method of claim 1, wherein destaging the first metadata journal further comprises:

suspending, before destaging the first metadata journal begins, at least one activity capable of changing the contents of the first metadata journal;

destaging the first metadata journal;

changing the mapping in the first table to point instead to a first respective artificial hash digest, the first respective artificial hash digest associated with a respective first version of the artificial hash digest, whereby the contents of the first metadata journal that was destaged are protected from alteration after the checkpoint is created; and

resuming the at least one activity capable of changing the contents of the first metadata journal.

3. The computer-implemented method of claim 2, further comprising:

defining a predetermined respective artificial hash digest to be a default version of the first respective hash digest; and

after the first metadata journal is destaged, modifying the mapping in the First table to point instead to the default version of the first respective hash digest.

4. The computer-implemented method of claim 1, further comprising reserving in the storage system a first region of available storage space, the first region of available storage space configured for storing information associated with I/O requests from the host that occur during and after creation of the checkpoint.

5. The computer-implemented method of claim 1, wherein destaging the second metadata journal further comprises:

disabling, before destaging the second metadata journal begins, at least one activity capable of changing information associated with an existing hash digest to physical layout mapping;

destaging the second metadata journal; and

resuming the at least one activity.

6. The computer-implemented method of claim 5, wherein the at least one activity comprises defragmentation.

7. The computer-implemented method of claim 1, further comprising:

performing, prior to a creation of the online system checkpoint, a defragmentation on at least a first region of storage space on the storage device, the defragmentation freeing a first portion of storage space in the flail respective first region of storage space; and

redirecting, during and after creation of the online system checkpoint, at least a portion of the host I/O requests away from at least one of the first, second, and third metadata journals, wherein the at least a portion of host I/O requests are instead directed to the first portion of storage space freed by the defragmentation of the first region of available storage space.

8. The computer-implemented method of claim 7, wherein the third metadata journal is not destaged until after host I/O has been configured to be redirected to the first portion of storage space.

9. The computer-implemented method of claim 1, wherein the destaging of the third metadata journal is configured to be able to occur concurrently with host writes.

10. A system, comprising;

a processor; and

a non-volatile memory in operable communication with the processor and storing computer program code that when executed on the processor causes the processor to execute a process operable to perform the operations of;

configuring a storage system responsive to input/output (I/O) requests to the storage device from a host in operable communication with the storage system;

configuring on the storage system first, second, and third tables and first, second, and third respective metadata journals associated with the first, second, and third, tables, each respective metadata journal configured to store respective contents, wherein;

the first table maps a first respective logical address associated with a first respective logical unit number (LUN) associated with the storage system to a corresponding first respective hash digest, the first respective hash digest computed based at least in part on data that resides at the first respective logical address;

the first metadata journal comprises first metadata configured to store information associated with time-based changes to information stored in the first table;

the second table maps a first range of respective hash digests to respective associated physical locations on the storage device;

the second metadata journal comprises second metadata configured to store information associated with time-based changes to information stored in the second table;

the third table comprises a mapping indicative of whether or not a given disk block on the storage device is allocated; and

the third respective metadata journal comprises third metadata configured to store information associated with time-based changes to information stored in the third table;

creating, while the storage system is online and responsive to I/O requests from the host, an online system checkpoint comprising information relating to a state of the storage system at a first point in time, the creation of the checkpoint comprising;

creating a plurality of consistent snapshots of the storage system at the first point in time; and

destaging, in order, the first metadata journal, the second metadata journal, and the third metadata journal, wherein each destaging is configured to destage information stored in the journal up to the first point in time.

11. The system of claim 10, further comprising computer program code that when executed on the processor causes the processor to execute a process operable to perform the operations of:

suspending, before destaging the first metadata journal begins, at least one activity capable of changing the contents of the first metadata journal;

destaging the first metadata journal;

changing the mapping in the first table to point instead to a first respective artificial hash digest, the first respective artificial hash digest associated with a respective first version of the artificial hash digest, whereby the contents of the first metadata journal that was destaged are protected from alteration after the checkpoint is created; and

resuming the at least one activity capable of changing the contents of the first metadata journal.

12. The system of claim 11, further comprising computer program code that when executed on the processor causes the processor to execute a process operable to perform the operations of:

defining a predetermined respective artificial hash digest to be a default version of the first respective hash digest; and

after the first and second metadata journals are destaged, modifying the mapping in the first table to point instead to the default version of the first respective hash digest.

13. The system of claim 10, further comprising computer program code that when executed on the processor causes the processor to execute a process operable to perform the operation of reserving in the storage system a first region of available storage space, the first region of available storage space configured for storing information associated with I/O requests from the host that occur during creation of the checkpoint.

14. The system of claim 10, further comprising computer program code that when executed on the processor causes the processor to execute a process operable to perform the operations of:

disabling, before destaging the second metadata journal begins at least one activity capable of changing information associated with an existing hash digest to physical layout mapping;

destaging the second metadata journals; and

resuming the at least one activity.

15. The system of claim 10, further comprising computer program code that when executed on the processor causes the processor to execute a process operable to perform the operations of:

performing, prior to a creation of the online system checkpoint, a defragmentation on at least a first region of storage space on the storage device, the defragmentation freeing a first portion of storage space in the respective first region of storage space; and

redirecting, during and after creation of the online system checkpoint, at least a portion of the host I/O requests away from at least one of the first, second, and third metadata journals, wherein the at least a portion of host I/O requests are instead directed to the first portion of storage space freed by the defragmentation of the first region of available storage space.

16. The system of claim 15, further comprising computer program code that when executed on the processor causes the processor to execute a process operable to perform the operation of ensuring that the third metadata journal is not destaged until after host I/O has been configured to be redirected to the first portion of storage space.

17. The system of claim 10, further comprising computer program code that when executed on the processor causes the processor to execute a process operable to perform the operations of destaging of the third metadata journal so as to be able to occur concurrently with host writes.

18. A computer program product including a non-transitory computer readable storage medium having computer program code encoded thereon that when executed on a processor of a computer causes the computer to operate a storage system, the computer program product comprising:

computer program code for configuring a storage system comprising a processor in operable communication with a storage device, the storage system responsive to input/output (I/O) requests to the storage device from a host in operable communication with the storage system;

computer program code for configuring on the storage system first, second, and third tables and first, second, and third respective metadata journals associated with the first, second, and third, tables, each respective metadata journal configured to store respective contents, wherein;

the first table maps a first respective logical address associated with a first respective logical unit number (LUN) associated with the storage device to a corresponding first respective hash digest, the first respective hash digest computed based at least in part on data that resides at the first respective logical address;

the first metadata journal comprises first metadata configured to store information associated with time-based changes to information stored in the first table;

the second table maps a first range of respective hash digests to respective associated physical locations on the storage device;

the second metadata journal comprises second metadata configured to store information associated with time-based changes to information stored in the second table;

the third table comprises a mapping indicative of whether or not a given disk block on the storage device is allocated; and

the third respective metadata journal comprises third metadata configured to store information associated with time-based changes to information stored in the third table; and

computer program code for creating, while the storage system is online and responsive to I/O requests from the host, an online system checkpoint comprising information relating to a state of the storage system at a first point in time, the creation of the checkpoint comprising;

creating a plurality of consistent snapshots of the storage system at the first point in time; and

destaging, in order, the first metadata journal, the second metadata journal, and the third metadata journal, wherein each destaging is configured to destage information stored in the journal up to the first point in time.

19. The computer program product of claim 18, further comprising:

computer program code for, before destaging the first metadata journal begins, suspending at least one activity capable of changing the contents of the first metadata journal;

computer program code for destaging the first metadata journal;

computer program code for changing the mapping in the first table to point instead to a first respective artificial hash digest, the first respective artificial hash digest associated with a respective first version of the artificial hash digest, whereby the contents of the first metadata journal that was destaged are protected from alteration after the checkpoint is created; and

computer program code for resuming the at least one activity capable of changing the content of the first metadata journal.

20. The computer program product of claim 19, further comprising:

computer program code for defining a predetermined respective artificial hash digest to be a default version of the first respective hash digest; and

computer program code for modifying, after the first and second metadata journals are destaged, the mapping in the first table to point instead to the default version of the first respective hash digest.