Synchronizing RAID configuration changes across storage processors

Patent metadata

Field	Value
Publication number	US-10146646-B1
Application number	US-201715498847-A
Country	US
Kind code	B1
Filing date	Apr 27, 2017
Priority date	Apr 27, 2017
Publication date	Dec 4, 2018
Grant date	Dec 4, 2018

Abstract

A technique for maintaining RAID (redundant array of independent disks) configuration metadata across multiple SPs (storage processors) includes receiving a change request by a controller within a first SP, writing, by the first SP, a RAID configuration change described by the change request to a persistent intent log, and informing a second SP that the intent log has been written. The second SP, upon being informed of the write to the intent log, reads the RAID configuration change from the intent log and writes the RAID configuration change to a persistent configuration database. In this manner, the first SP and the second SP both receive the RAID configuration change and thus are both equipped to service reads and writes directed to a affected RAID storage.

First claim

What is claimed is:

1. A method of maintaining configuration data describing RAID (redundant array of independent disks) storage across first and second SPs (storage processors) coupled to the RAID storage, the method comprising:
receiving, by a first controller running on the first SP, a change request to make a change in RAID configuration metadata describing the RAID storage;
in response to receiving the change request, (i) writing, by the first SP, a configuration-change record to a persistent intent log, the configuration-change record describing the requested change in RAID configuration metadata, and (ii) informing, by the first SP, a second controller running on the second SP that the configuration-change record has been written;
reading, by the second SP, the configuration-change record from the persistent intent log; and
writing, by the second SP, the configuration-change record as read from the persistent intent log to a persistent configuration database, the persistent intent log and the persistent configuration database each stored externally to the first SP and the second SP.

2. The method of claim 1 , wherein the RAID storage includes multiple disk drives, and wherein the persistent intent log and the persistent configuration database are each stored among the multiple disk drives of the RAID storage.

3. The method of claim 2 , wherein the multiple disk drives each include a first region reserved for system metadata and a second region for storing host data, and wherein the persistent intent log and the persistent configuration database are stored in the regions reserved for system metadata.

4. The method of claim 2 , further comprising:
storing, on each of the first SP and the second SP, a respective in-memory intent log;
in response to receiving the change request, writing, by the first controller, the configuration-change record to the in-memory intent log of the first SP; and
after reading, by the second SP, the configuration-change record from the persistent intent log, writing, by the second controller, the configuration-change record to the in-memory intent log of the second SP.

5. The method of claim 4 , further comprising:
storing, on each of the first SP and the second SP, a respective in-memory configuration database;
after writing, by the second SP, the configuration-change record as read from the persistent intent log to the persistent configuration database, writing, by the second controller, the configuration-change record to the in-memory configuration database of the second SP; and
in response to receiving a message from the second SP that the configuration-change record has been written to the in-memory configuration database of the second SP, writing, by the first controller, the configuration-change record to the in-memory configuration database of the first SP.

6. The method of claim 5 , wherein the first SP and the second SP each store (i) a first set of flags that indicates actions completed by the first SP in responding to the change request and (ii) a second set of flags that indicates actions completed by the second SP in responding to the change request.

7. The method of claim 6 , wherein informing, by the first SP, the second controller running on the second SP that the persistent intent log has been changed includes sending the first set of flags to the second SP.

8. The method of claim 7 , wherein receiving the message from the second SP includes receiving, by the first SP, the second set of flags from the second SP.

9. The method of claim 5 , further comprising:
receiving, by the first controller, a second change request to make a change in RAID configuration metadata;
in response to receiving the second change request, (i) writing, by the first SP, a second configuration-change record to the persistent intent log and (ii) informing, by the first SP, the second controller that the second configuration-change record has been written to the persistent intent log;
receiving, by the first SP, a notification that the second SP is down; and
in response to receiving the notification that the second SP is down, writing, by the first SP, the second configuration-change record to the persistent configuration database.

10. The method of claim 5 , further comprising:
receiving, by the first controller, a third change request to make a change in RAID configuration metadata;
in response to receiving the third change request, (i) writing, by the first SP, a third configuration-change record to the persistent intent log and (ii) informing, by the first SP, the second controller that the third configuration-change record has been written to the persistent intent log;
receiving, by the second SP, a notification that the first SP is down; and
in response to receiving the notification that the first SP is down, writing, by the second SP, the third configuration-change record to the persistent configuration database.

11. The method of claim 5 , further comprising:
receiving, by the first controller, a fourth change request to make a change in RAID configuration metadata;
in response to receiving the fourth change request, (i) writing, by the first SP, a fourth configuration-change record to the persistent intent log and (ii) informing, by the first SP, the second controller that the fourth configuration-change record has been written to the persistent intent log; and
in response to both the first SP and the second SP going down and after one of the first SP and the second SP has rebooted, synchronizing, by the rebooted SP, the fourth configuration-change record stored in the persistent intent log to the persistent configuration database.

12. A data storage system, comprising a first SP (storage processor) and a second SP coupled to RAID (redundant array of independent disks) storage, the data storage system constructed and arranged to:
receive, by a first controller running on the first SP, a change request to make a change in RAID configuration metadata describing the RAID storage;
in response to receiving the change request, (i) write, by the first SP, a configuration-change record to a persistent intent log, the configuration-change record describing the requested change in RAID configuration metadata, and (ii) inform, by the first SP, a second controller running on the second SP that the configuration-change record has been written;
read, by the second SP, the configuration-change record from the persistent intent log; and
write, by the second SP, the configuration-change record as read from the persistent intent log to a persistent configuration database, the persistent intent log and the persistent configuration database each stored externally to the first SP and the second SP.

13. A computer program product including a set of non-transitory, computer-readable media having instructions which, when executed by first and second SPs (storage processors) of a data storage system, cause the SPs to perform a method of maintaining configuration data across the first and second SPs, the method comprising:
receiving, by a first controller running on the first SP, a change request to make a change in RAID (redundant array of independent disks) configuration metadata describing RAID storage;
in response to receiving the change request, (i) writing, by the first SP, a configuration-change record to a persistent intent log, the configuration-change record describing the requested change in RAID configuration metadata, and (ii) informing, by the first SP, a second controller running on the second SP that the configuration-change record has been written;
reading, by the second SP, the configuration-change record

Assignees

• Emc Ip Holding Co Llc

Inventors

• Foley Robert P
• Puhov Peter
• Heng Socheavy

Classifications

• G06F3/0629

  Configuration or reconfiguration of storage systems · CPC title

• G06F3/0689 Primary

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

• G06F11/1474

  in transactions (updating of structured data in databases G06F16/23) · CPC title

• G06F2201/85

  Active fault masking without idle spares · CPC title

• G06F11/3051

  Monitoring arrangements for monitoring the configuration of the computing system or of the computing system component, e.g. monitoring the presence of processing resources, peripherals, I/O links, software programs (verification or detection of system hardware configuration G06F11/2247) · CPC title