Storage system with virtual volume having data arranged astride storage devices, and volume management method

Patent metadata

Field	Value
Publication number	US-9639277-B2
Application number	US-201514803247-A
Country	US
Kind code	B2
Filing date	Jul 20, 2015
Priority date	Feb 10, 2012
Publication date	May 2, 2017
Grant date	May 2, 2017

Abstract

A virtual LU astride a plurality of storage devices is a virtual volume composed of a plurality of partial volumes. Functions of the storage system, Zoning information of a SAN and a host group information of the virtual volume are inherited to a partial volume created for each physical device. When a page granularity data migration is executed, volume or data are migrated to other storage devices without depending on the relationship between a physical port and the physical device. When a host IO request is received when migration is on-going, response processing is performed by synchronizing storage devices within the range of migration data. The host IO request related to the page being migrated sends a partial complete response including information for re-routing the request to a path of the appropriate data migration destination device capable of issuing the IO.

First claim

The invention claimed is:

1. A system comprising:
a host system; and
a plurality of storage systems providing a distributed virtual volume to the host system;
wherein each of the plurality of storage systems is configured to manage a volume constituting a portion of the distributed virtual volume;
wherein the host system is configured to manage hit/miss information regarding IO (Input/Output) hit and IO miss of IO requests issued to destinations for accessing the distributed virtual volume, and
wherein the host system is configured to:
issue a first IO request to one of destinations for accessing a first portion of the distributed virtual volume on the basis of the hit/miss information;
update the hit/miss information on the basis of IO hit or IO miss of the first IO request; and
issue a second IO request to another one of the destinations for accessing the first portion of the distributed virtual volume on the basis of the updated hit/miss information, in case that IO miss of the first IO request occurred;
wherein the destinations for accessing the distributed virtual volume are target ports of the plurality of storage systems for accessing each volume constituting a portion of the distributed virtual volume;
wherein each volume stores target port group information including the target ports and access statuses of the target ports to control IO destinations of the IO requests; and
wherein the access status of all target ports associated with a target port group is identical and is changed simultaneously.

2. The system according to claim 1 , wherein the host system is configured to issue the second IO request to the one of the destinations for accessing the first portion of the distributed virtual volume on the basis of the updated hit/miss information, in case that IO hit of the first IO request occurred.

3. The system according to claim 1 ,
wherein IO hit of the first IO request indicates that the first IO request succeeded, and
wherein IO miss of the first IO request indicates that the first IO request failed.

4. The system according to claim 1 , wherein the access status of all target ports associated with a target port group is changed explicitly by the host system or implicitly by a multipath software of the host system issuing the IO requests.

5. The system according to claim 1 ,
wherein the one of the destinations, to which the first IO request was issued, for accessing the first portion of the distributed virtual volume is a target port of one of the plurality of storage systems, and
wherein the another one of the destinations, to which the second IO request was issued, for accessing the first portion of the distributed virtual volume is another target port of another one of the plurality of storage systems, in case that IO miss of the first IO request occurred.

6. The system according to claim 5 , wherein when the one of the plurality of storage systems does not manage a first volume constituting the first portion of the distributed virtual volume, the first IO request issued to the target port of one of the plurality of storage systems failed.

7. The system according to claim 5 , wherein when the one of the plurality of storage systems manages a first volume constituting the first portion of the distributed virtual volume, the first IO request issued to the target port of one of the plurality of storage systems succeeded.

8. The system according to claim 5 ,
wherein one of the plurality of storage systems manages a first volume constituting the first portion of the distributed virtual volume, and
wherein another one of the plurality of storage systems manages a second volume constituting a second portion of the distributed virtual volume.

9. The system according to claim 5 ,
wherein the one of the plurality of storage systems manages a first volume constituting the first portion of the distributed virtual volume,
wherein the system executes data migration of the first volume from the one of the plurality of storage systems to the another one of the plurality of storage systems,
wherein if the host system issued the first IO request to the target port of the one of the plurality of storage systems for accessing the first portion of the distributed virtual volume before the migration of the first volume, the first IO request succeeded, and
wherein if the host system issued the first IO request to the target port of the one of the plurality of storage systems for accessing the first portion of the distributed virtual volume after the migration of the first volume, the first IO request failed.

10. The system according to claim 1 ,
wherein one of the plurality of storage systems manages a first volume constituting the first portion of the distributed virtual volume, and
wherein another one of the plurality of storage systems manages a second volume constituting a second portion of the distributed virtual volume.

11. The system according to claim 1 ,
wherein the access statuses include an Active/Optimized (Act/Opt) state, an Active/Non-optimized (Act/Non) state, a Standby state, an Unavailable state, a Logical Block Dependent (LBD) state, an Offline state, and a Transitioning Between state (Transition).

12. The system according to claim 1 ,
wherein each target port is used to access one volume; and
wherein the access status of each target port is identical to the access status of the target port group with which said each target port is associated.

13. The system according to claim 1 ,
wherein at least one target port is used to access a plurality of volumes; and
wherein the access status of said at least one target port for one of the volumes is different from the access status of said at least one target port for another one of the volumes.

14. The system according to claim 1 ,
wherein at least one target port is associated with a plurality of target port groups for accessing a plurality of volumes; and
wherein the access status of one of the target port groups for accessing one of the volumes is different from the access status of another one of the target port groups for accessing another one of the volumes.

15. The system according to claim 1 , further comprising:
a network connected between the host system and the plurality of storage systems.

16. The system according to claim 15 ,
wherein the network is a storage area network.

Assignees

• Hitachi Ltd

Inventors

• Nakajima Akio

Classifications

• G06F3/0605

  by facilitating the interaction with a user or administrator · CPC title

• G06F3/0637

  Permissions · CPC title

• G06F3/0665

  at area level, e.g. provisioning of virtual or logical volumes · CPC title

• G06F3/0617 Primary

  in relation to availability · CPC title

• G06F3/067

  Distributed or networked storage systems, e.g. storage area networks [SAN], network attached storage [NAS] · CPC title