Achieving data consistency with point-in-time copy operations in a parallel I/O environment

• US 7,930,477 B2
• Filed: 05/21/2008
• Issued: 04/19/2011
• Est. Priority Date: 01/21/2005
• Status: Expired due to Fees

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Wilson, Steven B., Wightwick, Glenn R., Jones, Carl E.
• Primary Examiner(s): Thai; Tuan V.
• Application Number:
  US12/124,203
• Publication Number:
  US 20080222377A1
• Time in Patent Office: 1,063 Days
• Field of Search: 711/100, 711/114, 711/154, 711/161, 711/162, 711/201, 711/202, 711/203, 711/204
• US Class Current: 711/114
• CPC Class Codes: G06F 11/1458 Management of the backup or restore process
• CPC Class Codes: G06F 11/2094 Redundant storage or storage space G06F11/2056 takes precedence
• CPC Class Codes: G06F 11/2097 maintaining the standby controller/processing unit updated initialisation or re-synchronisation thereof G06F11/1658 and subgroups
• CPC Class Codes: G06F 3/0605 by facilitating the interaction with a user or administrator
• CPC Class Codes: G06F 3/065 Replication mechanisms
• CPC Class Codes: G06F 3/0659 Command handling arrangements, e.g. command buffers, queues, command scheduling
• CPC Class Codes: G06F 3/067 Distributed or networked storage systems, e.g. storage area networks [SAN], network attached storage [NAS]

Abstract

A method for processing a point-in-time copy of data associated with a logical storage volume where the data to be copied is stored in a striped or parallelized fashion across more than one physical source volume. The method includes receiving a point-in-time copy command concerning a logical volume and distributing the point-in-time copy command in-band to each of the physical source volumes containing a portion of the striped data. The method also includes establishing a point-in-time copy relationship between each physical source volume and one of a corresponding set of multiple physical target volumes. The method further includes copying the data stored on each physical source volume to the corresponding physical target volume. The in-band copy command and the striped data may be distributed over I/O channels between a server and the physical storage and processed sequentially.

Claims

1. A data storage system comprising:

a storage server operable to process an I/O write command and a point-in-time copy command each with respect to first data associated with a logical storage volume;

in-band I/O channels;

multiple physical source volumes in communication with the storage server through the in-band I/O channels, each physical source volume capable of being established in a point-in-time copy relationship with one of corresponding multiple physical target volumes;

a logical volume manager associated with the storage server operable to parallelize the first data and distributing a portion of the first data over one of the in-band I/O channels for writing to each of the multiple physical source volumes in a striped fashion, the logical volume manager being further operable to distribute the point-in-time copy command to each of the physical source volumes over one of the in-band I/O channels, whereby execution of the point-in-time copy command is completed by one of the physical source volumes prior to the second data being stored to the one of the multiple physical source volumes to update the first data.

2. The data storage system of claim 1 further comprising:

means for receiving multiple updates to the first data;

means for receiving multiple point-in-time copy commands concerning the multiple updates with the multiple point-in-time copy commands and multiple updates being received in a sequence;

means for parallelizing the updates;

means for distributing the updates to each of the physical source volumes;

means for distributing the point-in-time copy commands to each of the physical source volumes; and

means for writing the updates to each physical source volume and executing the point-in-time copy commands with respect to each physical source volume in accordance with the sequence, whereby an update is stored to a physical source volume only after a previous update is copied from the physical source volume to the corresponding physical target volume.

3. An article of manufacture for use in programming a data storage system to process a point-in-time copy of data associated with a logical storage volume, the article of manufacture comprising instructions for:

receiving first data associated with a logical volume;

sending the first data over I/O channels in a striped fashion for storage across more than one physical source volume;

storing the first data on the more than one physical source volume;

receiving a first point-in-time copy command concerning the first data;

distributing the first point-in-time copy command over the I/O channels to each of the physical source volumes;

establishing a point-in-time copy relationship between each physical source volume and a corresponding one of a set of more than one physical target volumes;

receiving second data associated with the logical volume to update the first data;

sending the second data over the I/O channels in a striped fashion for storage across the more than one physical source volume;

executing the distributed first point-in-time copy command by copying the first data stored on each physical source volume to the corresponding physical target volume; and

storing the second data on a physical source volume after the first data has been copied to the corresponding physical target volume.

4. The article of manufacture of claim 3, wherein the I/O channels comprise in-band I/O channels maintained between a storage controller and the physical source volumes and across which read and write I/O operations are distributed.

5. The article of manufacture of claim 3 further comprising instructions for:

receiving multiple updates to the first data associated with the logical volume;

receiving multiple point-in-time copy commands concerning the multiple updates with the multiple point-in-time copy commands and multiple updates being received in a sequence;

parallelizing the updates;

distributing the updates to each of the physical source volumes;

distributing the point-in-time copy commands to each of the physical source volumes; and

writing the updates to each physical source volume and executing the point-in-time copy commands with respect to each physical source volume in accordance with the sequence, whereby an update is stored to a physical source volume only after a previous update is copied from the physical source volume to the corresponding physical target volume.