Selecting a virtual tape server in a storage system to provide data copy while minimizing system job load

• US 9,886,211 B2
• Filed: 07/01/2010
• Issued: 02/06/2018
• Est. Priority Date: 10/07/2009
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Iwasaki, Norie, Katori, Katsuyoshi, Nohta, Takeshi, Taguchi, Kohei, Tosaka, Eiji
• Primary Examiner(s): Chery, Mardochee
• Application Number:
  US13/500,842
• Publication Number:
  US 20120203964A1
• Time in Patent Office: 2,777 Days
• Field of Search: 711113, 718102
• 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 11/2097 maintaining the standby controller/processing unit updated initialisation or re-synchronisation thereof G06F11/1658 and subgroups
• CPC Class Codes: G06F 2206/1012 Load balancing
• CPC Class Codes: G06F 3/061 Improving I/O performance
• CPC Class Codes: G06F 3/0614 Improving the reliability of storage systems
• 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 3/0683 Plurality of storage devices
• CPC Class Codes: G06F 3/0686 Libraries, e.g. tape libraries, jukebox

Abstract

In a storage system including plural source storage devices, a target storage device selects which source storage device to accept a copy request from the target storage device so as to minimize the load on the entire system. The system calculates first and second load values for job loads being processed. System load values for the system are derived from job load value of a specific data, and respective load values for first and second source storage devices. The system compares the system load values to select a storage device to provide the data copy so as to minimize the load on the entire system.

Claims

1. A virtual tape server storage system comprising:

a plurality of storage devices communicatively connected with each other;

a plurality of source storage devices including at least a first source storage device and a second source storage device each processing data volumes in response to copy request jobs from other storage devices, and holding a job list of the data volumes being processed and attribute information thereof; and

a target storage device requesting a copy of data from one of the plurality of source storage devices, wherein said one of the plurality source storage devices is selected before commencement of processing the data volumes based on the attribute information so as to minimize system job load;

wherein the selection of said one of the first and second source storage devices comprises;

(a) calculating first and second load values representing job loads processed, respectively, by the first and second source storage devices;

(b) adding a job load value for said data respectively to the first and second load values to obtain a first final load value for the first source storage device and a second final load value for the second source storage device, respectively;

(c) adding the second load value to the first final load value to obtain a first total system load value for the storage system;

(d) adding the first load value to the second final load value to obtain a second total system load value for the storage system;

(e) comparing the first total system load value with the second total system load value;

(f) selecting said one of the first and second source storage devices based on the comparison to minimize the system job load; and

(g) requesting the copy of data from said one of the first and second source storage devices.

2. The storage system according to claim 1, wherein the attribute information includes a processing ability value (RA) for each job processed by the source storage devices, unprocessed data amounts (Ci=C1, C2, . . . , CN) and priorities (Pi=P1, P2, . . . , PN) associated with data volume numbers in the job list, where N is the number of jobs.

3. The storage system according to claim 2, wherein the first and second source storage devices process data volumes in parallel based on a processing ability value (RA/N) equally assigned to each of the processing ability values of the data volumes being processed.

4. The storage system according to claim 3, wherein the first load value, the second load value, and the load value of the data are calculated based on the processing ability value, the unprocessed data amount for each data volume being processed by the source storage devices, and the priority of each job.

5. The storage system according to claim 4, wherein the first load value, the second load value, and the load value of the data are given as a sum of values each calculated by dividing the assigned processing ability value (RA/N) into a value resulting from multiplying the unprocessed data amount (Ci) for each data volume by each priority (Pi=high priority (H) or low priority (L)).

6. The storage system according to claim 5, wherein the first load value, the second load value, and the load value W of the data are given as W=Σ

ci×

Pi/(RA/N).

7. The storage system according to claim 6, wherein the priority value is such that a high priority value is larger than a low priority value.

8. The storage system according to claim 7, wherein the high priority value is approximately 0.8 and the low priority value is approximately 0.2.

9. The storage system according to claim 5, wherein the priority value is given by the attribute information set by a user in the data volume, and determined based on one of a Run mode and a Deferred mode at a time of the copy request.

10. The storage system according to claim 1, wherein the storage devices includes a DASD cache.

11. The storage system according to claim 10, wherein the DASD cache is coupled to a tape drive and functions as a high-speed cache of the tape drive.

12. A virtual tape server storage system comprising:

a plurality of storage devices communicatively connected with each other;

a plurality m source storage devices (where m>

=2) each processing data volumes in response to copy request jobs from other storage devices, and holding a job list of the data volumes being processed and attribute information thereof; and

a target storage device requesting a copy of data from one of the plurality m source storage devices, wherein said one of the plurality m source storage devices is selected before commencement of processing the data volumes based on the attribute information so as to minimize system job load;

wherein the selection of said one of the m source storage devices comprises;

(a) calculating load values representing job loads respectively processed by the m source storage devices based on the attribute information;

(b) adding a job load value of the data to the load value for each of the m source storage devices to obtain a final load value for each of the m source storage devices, respectively;

(c) adding, to one final load value for one of the source storage devices, all the other load values to obtain a total system load value for the storage system;

(d) executing step (c) on the final load values for each of the m source storage devices to obtain the final total system load values corresponding to the m source storage devices, respectively;

(e) comparing the m total system load values;

(f) selecting said one of the m source storage devices based on the comparison to minimize the system job load; and

(g) requesting the copy of data from said one of the m source storage devices.

13. A computer program product for selecting an optimal source storage device as a copy request destination of data in a virtual tape server storage system including a plurality of storage devices communicatively connected with each other, a plurality m source storage devices each processing data volumes in response to copy request jobs from other storage devices, and holding a job list of the data volumes being processed and attribute information thereof, and a target storage device requesting the copy of data from one of the plurality m source storage devices, the computer program product comprising a non-transitory computer readable storage medium having computer readable program code embodied therewith and configured to:

(a) calculate load values representing job loads being processed by the plurality m source storage devices based on the attribute information, respectively;

(b) add a job load value of the data respectively to the load value for each of the plurality m source storage devices to obtain a final load value for said each of the plurality m source storage devices, respectively;

(c) add to the final load value all the other load values to obtain a total system load value for the storage system;

(d) execute step (c) for each of the m source storage devices to obtain the final total system load values for the plurality m source storage devices, respectively;

(e) compare the obtained final total system load values;

(f) before commencement of processing the data volumes, select said one of the plurality m source storage devices based on the comparison to minimize the system job load; and

(g) requesting the copy of data from said one of the m source storage devices.