Controller-based bi-directional remote copy system with storage site failover capability

• US 6,643,795 B1
• Filed: 03/30/2000
• Issued: 11/04/2003
• Est. Priority Date: 03/30/2000
• Status: Expired due to Term

• Current Assignee: Hewlett Packard Enterprise Development LP (Hewlett-Packard Enterprise Company)
• Original Assignee: Hewlett-Packard Development Company, L.P. (HP Inc.)
• Inventors: Sicola, Stephen J., Elkington, Susan G.
• Primary Examiner(s): Beausoliel, Robert
• Assistant Examiner(s): DUNCAN, MARC M
• Application Number:
  US09/538,680
• Time in Patent Office: 1,314 Days
• Field of Search: 714/6, 714/11, 714/5, 714/4, 714/7, 714/13
• US Class Current: 714/6.21
• CPC Class Codes: G06F 11/2005 using redundant communication controllers
• CPC Class Codes: G06F 11/2007 using redundant communication media
• CPC Class Codes: G06F 11/2023 Failover techniques
• CPC Class Codes: G06F 11/2035 without idle spare hardware
• CPC Class Codes: G06F 11/2069 Management of state, configuration or failover
• CPC Class Codes: G06F 11/2071 using a plurality of controllers
• CPC Class Codes: G06F 11/2079 Bidirectional techniques
• CPC Class Codes: G06F 11/2082 Data synchronisation
• CPC Class Codes: G06F 11/2089 Redundant storage control functionality
• CPC Class Codes: G06F 2201/855 Details of asynchronous mirroring using a journal to transfer not-yet-mirrored changes
• CPC Class Codes: H04L 67/1001 for accessing one among a plurality of replicated servers

Abstract

A data replication system having a redundant configuration including dual Fiber Channel fabric links interconnecting each of the components of two data storage sites, wherein each site comprises a host computer and associated data storage array, with redundant array controllers and adapters. The system includes the capability of simultaneous bi-directional remote data replication which permits the system to operate in an ‘extended cluster’ mode, as if each of the remote storage arrays were local relative to the respective remote host. The system further includes the concept of ‘home’ and ‘alternate’ storage nodes, which provide for automatic node failover from a primary to a designated alternate node, without necessitating re-booting of the remote node. Write data transfers are potentially host retry-able at both sites; upon failure of controllers at one site, the host re-issues the same write on other site.

Claims

1. In a bi-directional data replication system having two sites each including a host computer and a node comprising a pair of array controllers coupled to a data storage array, a method for determining the node at which data is potentially available, said method comprising:

establishing a home node and an alternate node for each said host computer in the bi-directional data replication system;

wherein each said host computer performs;

during normal operation, accessing the home node for data;

in the event of a failure in the home node where data cannot be accessed,

accessing the alternate node for data; and

when the home node again becomes operational, accessing the home node for data.

2. The method of claim 1, wherein, in said event of failure, the host computer for the node where the failure occurred initiates a node failover by a multi-path driver.

3. The method of claim 1, further comprising registering, with each said host computer, a unique identifier for each said node, to establish an association therebetween.

4. The method of claim 1, wherein the two sites are interconnected by two Fibre channel fabric links.

5. A method for bi-directional replication of data between two sites connected by two links, each site including a local host computer and a node comprising a pair of array controllers coupled to a local data storage array, the method comprising:

in the situation when either of said links is operational, and at least one cross-link array controller is in communication with its cross-link partner controller,

presenting logical units residing on each said local data storage array to each respective said local host computer wherein the logical units are part of a remote copy set contained on each said data storage array;

in the situation when both links are down, or when neither said pair of array controllers can communicate with its cross-link partner controller,

notifying each said host that all logical units that are part of remote copy sets are not available;

wherein, if a site failover occurs,

causing the logical units for the pair of controllers at both said sites to again be visible locally to each said host; and

logging data to a log unit for each logical unit;

waiting for a failback of the sites to occur; and

wherein, after said failback occurs,

initiating a merge operation from each said log unit to a corresponding remote copy set member at the other site; and

repeating the above beginning with presenting said logical units.

6. The method of claim 5, wherein said links comprise fibre channel fabric links.

7. A method for bi-directional replication of data between two sites connected by two fibre channel fabric links, each site including a local host computer and a node comprising a pair of array controllers coupled to a local data storage array, the method comprising:

in the situation when either of said links is operational, and at least one cross-link array controller is in communication with its cross-link partner controller,

presenting logical units residing on each said local data storage array to each respective said local host computer, wherein the logical units are part of a remote copy set contained on each said data storage array;

wherein, when both links are down, or when neither said pair of array controllers can communicate with its cross-link partner controller,

notifying each said host that all logical units that are part of remote copy sets are unavailable; and

causing the logical units for the pair of controllers at both said sites to again be visible locally to each said host after notification of site failover is provided.

8. The method of claim 7, after said site failover has occurred, further comprising:

logging data to a log unit for each logical unit;

waiting for a failback of the sites to occur; and

after said failback occurs, initiating a merge operation from each said log unit to a corresponding remote copy set member at the other site.

9. The method of claim 7, wherein said logical units residing on each said data storage array have the same logical name.

10. The method of claim 7, wherein exactly one said pair of array controllers is coupled to each said data storage array.

11. A method for simultaneous bi-directional replication of data between two sites connected by at least one link, each site including a local host computer and a local node comprising a pair of array controllers coupled to a local data storage array, the method comprising

simultaneous bi-directional replication of data between two sites;

including performing copy operations from each host computer to the node at the opposite side of said at least one link; and

performing data I/O operations from each host computer to the local node.

12. The method of claim 11, wherein said copy operations are performed to logical units that are part of a remote copy set contained on each said data storage array.

13. The method of claim 12, wherein said logical units that are part of a remote copy set share an identical logical name.

14. The method of claim 11, wherein exactly one said pair of array controllers is coupled to each said data storage array.

15. The method of claim 11, wherein said at least one link comprises two fibre channel fabric links.

16. The method of claim 11, wherein said link comprises a fibre channel fabric link.

17. The method of claim 11, wherein said replication is performed to migrate the data between the two sites.