Storage system, data processing method and storage apparatus

• US 7,558,916 B2
• Filed: 03/16/2006
• Issued: 07/07/2009
• Est. Priority Date: 02/01/2006
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Hitachi, Ltd.
• Inventors: Yukawa, Masashi, Nakama, Hironori, Kumasawa, Hiroyuki, Chikusa, Takashi, Yamaura, Satoru
• Primary Examiner(s): Ellis; Kevin L
• Assistant Examiner(s): Thammavong; Prasith
• Application Number:
  US11/376,060
• Publication Number:
  US 20070180168A1
• Time in Patent Office: 1,209 Days
• Field of Search: 711/114
• US Class Current: 711/114
• CPC Class Codes: G06F 11/1435 using file system or storage system metadata
• CPC Class Codes: G06F 11/1662 the resynchronized component or unit being a persistent storage device re-synchronization of failed mirror storage G06F11/2082; rebuild or reconstruction of parity RAID storage G06F11/1008
• CPC Class Codes: G06F 11/2092 Techniques of failing over between control units
• CPC Class Codes: G06F 11/2094 Redundant storage or storage space G06F11/2056 takes precedence
• CPC Class Codes: G06F 2201/84 Using snapshots, i.e. a logical point-in-time copy of the data
• CPC Class Codes: G06F 3/0617 in relation to availability
• CPC Class Codes: G06F 3/0626 Reducing size or complexity of storage systems
• CPC Class Codes: G06F 3/0635 by changing the path, e.g. traffic rerouting, path reconfiguration
• CPC Class Codes: G06F 3/0647 Migration mechanisms
• CPC Class Codes: G06F 3/0664 at device level, e.g. emulation of a storage device or system
• CPC Class Codes: G06F 3/067 Distributed or networked storage systems, e.g. storage area networks [SAN], network attached storage [NAS]
• CPC Class Codes: H04L 67/1097 for distributed storage of data in networks, e.g. transport arrangements for network file system [NFS], storage area networks [SAN] or network attached storage [NAS]
• CPC Class Codes: H04L 67/14 Session management for real-time applications in data packet communications networks H04L65/1066

Abstract

Proposed are a storage system, data processing method and storage apparatus capable of performing stable data I/O processing. Each of the storage apparatuses configured in the storage group stores group configuration information containing priority information given to each storage apparatus, and the storage apparatus with the highest priority becomes a master and performs virtualization processing and data I/O processing, and another storage apparatus belonging to this storage group performs internal processing of the storage group.

Claims

1. A storage system in which a plurality of storage apparatuses are connected to a network and configured into a plurality of storage groups,

wherein each of the storage apparatuses has a processor, a memory, a channel interface and a disk interface,

wherein each storage apparatus belongs to at least one of the storage groups, retains in the memory thereof configuration information of each of storage apparatuses in said at least one storage group, a priority number representing a priority of said each storage apparatus in each of said at least one storage group to become a substitute master when a failure occurs in a master storage apparatus in said each storage group, and management information of said at least one storage group, said configuration information and management information are common among all of said storage apparatuses configured in the same storage group,

wherein a first storage apparatus with the highest priority number in said each storage group is configured as said master storage apparatus whose processor performs virtualization processing of storage apparatuses in said each storage group by presenting said storage apparatuses in said each storage group as a single virtual storage apparatus to a host system, presenting volumes configured in memories of said respective storage apparatuses in said each storage group as at least primary and secondary virtual volumes of the single virtual storage apparatus to the host system, receiving data I/O processing requests designating said virtual volumes sent from the host system, and performing data I/O processing for a received data I/O processing request from the host system to said virtual storage apparatus which involves a volume configured in the memory of said master storage apparatus for data reading and writing requested by the host system,

wherein a second highest priority number is given to another one of the storage apparatuses in said storage group to become the substitute master when a failure occurs in the master storage apparatus, the priority numbers are either continuous or non-continuous integer numbers, and some of the priority numbers are shared by two or more of the storage apparatuses in said storage group, and

wherein a storage apparatus with the lowest priority number in an on-line storage group which directly conducts data input and output with the host system is also configured as a master storage apparatus in an archive storage group used as an archive of the on-line storage group.

2. The storage system according to claim 1, wherein said storage apparatus other than said first storage apparatus in said storage group does not reply that it is an operable storage apparatus to a discovery request from said host system.

3. The storage system according to claim 2, wherein said each storage apparatus belongs to the same storage group does not reply that it is an operable storage apparatus to a discovery request from another storage apparatus in the storage group with a priority in said storage group that is equal to or higher than said each storage apparatus.

4. The storage system according to claim 1, wherein a volume in said each storage apparatus virtualized by said first storage apparatus is disposed redundantly in said plurality of storage apparatuses configuring said same storage group.

5. The storage system according to claim 4, wherein, when the access from said host system is a data I/O request of files in said each storage apparatus virtualized in said storage group, the number of said storage apparatuses retaining metadata of said virtual volume is less than the number of said storage apparatuses configuring said virtual volume.

6. The storage system according to claim 1, wherein said second storage apparatus performs said data migration involving internal processing according to instructions from said first storage apparatus;

and

wherein said first storage apparatus transmits prescribed metadata to said second storage apparatus upon designating said internal processing to said second storage apparatus.

7. The storage system according to claim 6, wherein said second storage apparatus makes an inquiry to said first storage apparatus if it does not receive said metadata set to be transmitted from said first storage apparatus for over a certain period of time.

8. The storage system according to claim 1, wherein, when a failure occurs in said first storage apparatus or said second storage apparatus in said storage group, said storage apparatus with the next highest priority after said first storage apparatus or said second storage apparatus subject to said failure takes over the functions of said first storage apparatus or said second storage apparatus subject to said failure, based on said priority information of each of said storage apparatuses.

9. The storage system according to claim 1, wherein, when said each storage apparatus is configured to belong to a plurality of said storage groups, said each storage apparatus retains, per storage group, configuration information and priority information of each of said storage apparatuses configured in a respective one of said storage groups and management information of the respective storage group.

10. The storage system according to claim 9, wherein configuration information and priority information of each of said storage apparatuses configured in said respective storage group and management information of the respective storage group are configured to have different characteristics in each of said storage groups among said storage groups.

11. The storage system according to claim 9, wherein a storage apparatus in an online storage group which directly conducts the input and output of data with the host system is also configured as a constituent element of an archive storage group to be used as an archive.

12. The storage system according to claim 11, wherein said storage apparatus in the online storage group has the lowest priority number in the online storage group.

13. The storage system according to claim 11, wherein said storage apparatus is configured as a slave in the online storage group, and as a master in archive storage group for performing virtualization processing of said storage apparatuses in said archive storage group to present said storage apparatuses in said archive storage group as a single virtual storage apparatus to the host system.

14. The storage system according to claim 11, wherein said storage apparatus has different priority numbers and/or different identifiers in the online storage group and in archive storage group respectively.

15. The storage system according to claim 11, wherein said storage apparatuses in said archive storage group are configured as read only.

16. The storage system according to claim 1, wherein internal processings other than said virtualization processing of the storage apparatuses are performed with a second one of said storage apparatuses in said each storage group, and said second storage apparatus is configured to perform snapshots, mirroring or data migration involving internal processings on the remaining storage apparatuses in said storage group.

17. The storage system according to claim 16, wherein the remaining storage apparatuses in said each storage group are set as slave storage apparatuses, and the configuration information includes different QoS (Quality of Service) parameters set regarding a status as a master, submaster or slave.

18. The storage system according to claim 1, wherein each storage apparatus retains in the memory thereof a storage group identifier each identifying one of said at least one storage group.

19. The storage system according to claim 1, wherein each storage apparatus replies itself as an operable storage apparatus only to a discovery request from a storage apparatus having a priority number that is equal or higher than a priority number of its own, and does not reply to a discovery request issued from the host system.

20. A data processing method of a storage system in which a plurality of storage apparatuses are connected to a network, each of said storage apparatuses having a processor, a memory, a channel interface and a disk interface, said method comprising:

configuring said storage apparatuses into a plurality of storage groups, each of said storage apparatuses belonging to at least one of the storage groups;

storing in each of said storage apparatuses management information per storage apparatus of each of said storage apparatuses configured in the same storage group, and group configuration information formed from management information relating to the storage group, a priority number representing a priority of said each storage apparatus in the storage group to become a substitute master when a failure occurs in a master storage apparatus in the storage group, and management information of the storage group, said configuration information and management information are common among all of said storage apparatuses configured in the same storage group;

configuring a first storage apparatus with the highest priority in said storage group as said master storage apparatus whose processor performs virtualization processing of storage apparatuses in the storage group, by presenting said storage apparatuses in said each storage group as a single virtual storage apparatus to a host system, presenting volumes configured in memories of said respective storage apparatuses in said each storage group as at least primary and secondary virtual volumes of the single virtual storage apparatus to the host system, receiving data I/O processing requests designating said virtual volumes sent from the host system, and performing data I/O processing for a received data I/O request from the host system to said virtual storage apparatus which involves a volume configured in the memory of said master storage apparatus for data reading and writing requested by the host system;

giving a second highest priority number to another one of the storage apparatuses in said storage group to become the substitute master when a failure occurs in the master storage apparatus, the priority numbers being either continuous or non-continuous integer numbers, and some of the priority numbers being shared by two or more of the storage apparatuses in said storage group, and

configuring a storage apparatus with the lowest priority number in an on-line storage group which directly conducts data input and output with the host system also as a master storage apparatus in an archive storage group used as an archive of the on-line storage group.

21. The data processing method according to claim 20, wherein said second storage apparatus is given a priority that is next highest after said first storage apparatus.

22. The data processing method according to claim 21, further comprising when a failure occurs in said first storage apparatus or said second storage apparatus in said same storage group, taking over by a storage apparatus with the next highest priority after said first storage apparatus or said second storage apparatus subject to the failure said virtualization processing and said data I/O processing of said first storage apparatus, or said internal processing of said second storage apparatus subject to said failure.