JP5601480B2 - Storage device and data storage device replacement method for storage device - Google Patents

Description

  The present invention relates to a storage device and a data storage device replacement method for the storage device.

  Among storage apparatuses, a storage apparatus that configures RAID using a plurality of data storage apparatuses and maintains the redundancy of stored data is known. As a data storage device, an HDD (Hard Disk Drive) is often used, but recently, a device using an SSD (Solid State Drive) instead of the HDD has been proposed.

  The SSD has a feature that random access is fast because it does not have any components that operate inside like an HDD. Therefore, the problem that the data access speed of the storage apparatus becomes a bottleneck can be solved by using the SSD as the data storage apparatus.

  However, since SSD has a limit on the number of times data can be written, if the number of data writes reaches the limit number, data cannot be written, and RAID redundancy cannot be maintained.

  In order to solve such a problem, a storage device with a large number of data erasures can be replaced with a spare storage device, so that the number of write operations of the storage device can be leveled and the life of the entire storage system can be extended. Has been proposed (see Patent Document 1 below).

  More specifically, in this technique, a storage system including a plurality of storage devices for storing data is configured as follows. That is, a plurality of storage devices include spare storage devices, and storage device configuration information including the identifier of each storage device and the number of times data is erased from which data stored in each storage device is erased is stored in the storage system. The When the number of data erasures exceeds a predetermined threshold, the storage system copies the data stored in the storage device whose number of data erasures exceeds the predetermined threshold to the spare storage device, The identifier of the storage device in which the number of times of data erasure exceeds a predetermined threshold is assigned to the identifier of the spare storage device to which the data has been copied.

JP 2010-55247 A

  When the technology described in Patent Document 1 is used, the number of write operations of the storage device can be leveled. However, in a storage system, when a RAID is configured using, for example, SSD, a plurality of data is written at the time of data write. There is a possibility that the SSD reaches the write limit number at the same time. As a countermeasure against this, when the SSD reaches a predetermined number of times of writing before the number of times of writing limit, it may be configured to output a maintenance report to maintenance personnel so as to replace the SSD.

  However, after receiving the maintenance notification, it may be possible that the SSD reaches the write limit number before the maintenance staff replaces the SSD. Even when the SSD is replaced by maintenance personnel, the SSD is subjected to data restoration processing until the restoration operation is completed, but redundancy is lost during the restoration processing. If a failure occurs in another SSD constituting the RAID during the restoration process, the redundancy of the stored data cannot be maintained.

  The present invention has been made in view of the above circumstances, and its object is to prevent a plurality of data storage devices from simultaneously reaching the write limit number when a plurality of data storage devices constitute a RAID. An object of the present invention is to provide a disk array device and a data storage device replacement method for the disk array device that can prevent a situation in which a plurality of data storage devices reach the write limit count at the same time and cannot maintain redundancy. .

  The present invention is a storage device that maintains data redundancy by using a plurality of data storage devices that store data, and includes a spare data storage device and a first number that defines the number of writes to the data storage device A first threshold value storage unit that stores a second threshold value that defines a threshold value and the number of writes that is greater than the first threshold value and less than the write limit number of the data storage device; A write number storage unit that stores the number of data writes to the spare data storage device, and a first management unit that manages the data storage device and the spare data storage device. When writing data, the management unit determines whether or not the number of writes of the plurality of data storage devices has exceeded the first threshold. A first determination unit configured to determine based on the number of times of writing stored in the number storage unit, and the data storage device when the first determination unit determines that there is a data storage device exceeding the first threshold value A second determination unit that determines whether or not there are a plurality of data storage devices, and a second data storage device that selects one data storage device from the plurality of data storage devices when the second determination unit determines that there are a plurality of data storage devices. 1 selection means, first data writing means for writing data stored in the data storage device selected by the first selection means to the spare data storage device, and the first data writing means And a first reconfiguration unit configured to reconfigure the configuration for maintaining the redundancy using a spare data storage device in which data is written.

  Another aspect of the present invention is a data storage device replacement method for a storage device that uses a plurality of data storage devices for storing data to maintain data redundancy, the storage device comprising a spare data storage device, A first threshold that defines the number of writes to the data storage device and a second threshold that defines the number of writes that is greater than the first threshold and less than the write limit of the data storage device are stored. Managing a first threshold storage unit, a write count storage unit for storing the number of data writes to each data storage device and the spare data storage device, and the data storage device and the spare data storage device A first management unit, wherein the data storage device exchanging method includes a plurality of data when data is written. When there is a step of determining whether or not the number of writes of the storage device exceeds the first threshold based on the number of writes stored in the write number storage unit, and a data storage device that exceeds the first threshold If so, determining whether there are a plurality of data storage devices; if determining that there are a plurality of data storage devices, selecting one data storage device from the plurality of data storage devices; The step of writing the data stored in the selected data storage device to the spare data storage device and the configuration for maintaining the redundancy using the spare data storage device to which the data is written are reconfigured. And a step.

  According to the present invention, when a RAID is configured by a plurality of data storage devices, the plurality of data storage devices are prevented from reaching the write limit number at the same time, and the plurality of data storage devices reach the write limit number at the same time. Thus, it is possible to provide a disk array device and a data storage device replacement method for the disk array device that can prevent a situation where redundancy cannot be maintained.

It is a figure which shows the structure of the disk array apparatus based on the 1st Embodiment of this invention. It is a figure for demonstrating the structure of the SSD data copy threshold value table which concerns on the embodiment. It is a figure for demonstrating the structure of the SSD write frequency table based on the embodiment. It is a flowchart which shows the automatic exchange process of SSD which concerns on the embodiment. It is a figure which shows an example of the threshold value set to the SSD data copy threshold value table which concerns on the embodiment. It is a figure which shows an example of the SSD write frequency table which concerns on the embodiment. It is a figure which shows an example of the SSD write frequency table which concerns on the embodiment. It is a figure which shows an example of the SSD write frequency table which concerns on the embodiment. It is a figure which shows the structure of the disk array apparatus based on the 2nd Embodiment of this invention. It is a figure for demonstrating the structure of the SSD data copy threshold value table which concerns on the embodiment. It is a flowchart which shows the exchange process of SSD which concerns on the embodiment. It is a figure which shows an example of the threshold value set to the SSD data copy threshold value table which concerns on the embodiment. It is a figure which shows an example of the SSD write frequency table which concerns on the embodiment. It is a figure which shows an example of the SSD write frequency table which concerns on the embodiment. It is a figure which shows an example of the SSD write frequency table which concerns on the embodiment.

  Embodiments of the present invention will be described below with reference to the drawings.

(First embodiment)
FIG. 1 is a diagram showing a configuration of a disk array device that is a storage device. As shown in the figure, the disk array device 1 includes a controller 2, an SSD (Solid State Disk) 40 that is one or more data storage devices, and one or more spare data storage devices ( The disk unit 3 is composed of a spare disk 50 which is an SSD).

  The controller 2 is connected to one or a plurality of host devices 4 on which management software is installed. The controller 2 is connected to the host controller 5 that transmits / receives data to / from the host device 4, the disk controller 6 that is connected to the disk unit 3 and reads / writes data from / to the SSD 40, and the write that is the first management unit It includes a number monitoring unit 7, a data copy instruction unit 8, an SSD data copy threshold table 10 serving as a first threshold storage unit, and an SSD writing number table 20 serving as a writing number storage unit.

  The disk unit 40 includes a plurality of RAID configurations 60 each including a plurality of SSDs 40.

  FIG. 2 is a diagram for explaining the configuration of the SSD data copy threshold table 10. As shown in the figure, the SSD data copy threshold value table 10 stores a threshold value A11 and a threshold value B12 for determining whether or not to execute data copy of the SSD 40 described later. The threshold A11 defines a predetermined number of writes, and the threshold B12 defines a number of times larger than the threshold A11, and defines a number of writes smaller than the write limit number of the SSD 40. The threshold value A11 and the threshold value B12 can be changed from the management software installed in the host device 4 via the host control unit 5.

  FIG. 3 is a diagram for explaining the configuration of the SSD write count table 20. The SSD write count table 20 stores an SSD number 21 for identifying the SSD 40, a RAID configuration number 22 for identifying whether the configuration is the RAID configuration 60 or the spare disk 50, and the write count 23 in association with each other.

  The write count monitoring unit 7 is a management for managing the SSD 40 and the spare disk 50. Based on the number of writes of each SSD 40 stored in the SSD write count table 20, the write count monitoring unit 7 performs a process of replacing the SSD 40 with the increased number of writes with a spare disk 50. Details of this processing will be described later with reference to FIG.

  When the data copy instruction unit 8 receives an instruction from the write count monitoring unit 7 to copy the data of the SSD 40 to the spare disk 50, the data copy instruction unit 8 instructs the disk control unit 6 to copy the data from the SSD 40 to the spare disk 50. To do.

  The disk control unit 6 controls a writing process to each SSD 40 in the disk unit 3 and a data reading process from each SSD 40.

  Although the configuration of the disk array device 1 has been described above, the other disk array devices 1 except for the above-described write number monitoring unit 7, data copy instruction unit 8, SSD data copy threshold value table 10, and SSD write number table 20. The configuration is substantially the same as the configuration of a conventional disk array device, and is not directly related to the present invention, so the detailed configuration and description thereof will be omitted.

  Next, the processing shown in FIG. 4 for the process of replacing the SSD 40 of the disk array device 1 with the spare disk 50, the SSD data copy threshold table 10 of FIG. 5, and the SSD write count table 20 of FIGS. To explain.

  In the first embodiment, the write count limit of the SSD 40 is set to 100, and in the case of the spare disk 50, “FF” is stored as the RAID configuration number 22 of the write count table 20. When a data copy process described later is performed, the write count 23 is increased by 5 times.

  As shown in FIG. 4, when the data writing process from the host device 4 to the SSD 40 is executed, the controller 2 increases the number of writes of the SSD 40 that is a write target in the SSD write number table 20.

  Next, the write count monitoring unit 7 selects one RAID configuration number from the write count table 20 (S100).

  Next, the write count monitoring unit 7 determines whether or not the selection of the RAID configuration number is finished (S101). When it is determined that the selection of the RAID configuration number has been completed (S101: NO), in other words, when all the RAID configuration numbers have been selected and the processing described below has been completed, the write count monitoring unit 7 ends this processing. .

  On the other hand, when one RAID configuration number is selected (S101: YES), the write count monitoring unit 7 sets the write count 23 for the SSD 40 having the same RAID configuration number as the selected RAID configuration number. 20 are extracted (S102).

  For example, in the example illustrated in FIG. 6, when “00” is selected as the RAID configuration number, the write count monitoring unit 7 has the SSD 40 having the same RAID configuration number as the RAID configuration number “00”, that is, the SSD number. The write counts “85”, “82”, and “50” of 00, SSD number 01, SSD number 02 are extracted.

  Next, the write count monitoring unit 7 determines whether or not there is an SSD 40 whose write count exceeds the threshold A11 stored in the SSD data copy threshold table 10 among the extracted write counts 23 (S103: first) Judgment means).

  When it is determined that there is no SSD 40 whose write count exceeds the threshold A11 (S103: NO), the write count monitoring unit 7 sets the RAID configuration number to be checked to the next number (S104), and proceeds to the process of step S100 described above. Repeat the process described above.

  On the other hand, when it is determined that there is an SSD 40 whose write count exceeds the threshold A11 (S103: YES), the write count monitoring unit 7 further determines whether there are a plurality of SSDs 40 whose write count exceeds the threshold A11 (S105). : Second determination means).

  When it is determined that there are a plurality of SSDs 40 whose write count exceeds the threshold A11 (S105: YES), the write count monitoring unit 7 selects the SSD number of the SSD 40 with the largest write count among the extracted write counts ( S106: First selecting means).

  For example, in the example shown in FIG. 6, “85”, “82”, and “50” are extracted as the number of times of writing of the SSD number “00”, SSD number “01”, SSD number “02”. And the threshold value A11 “80” shown in FIG. In this example, since the number of times of writing “85” and “82” exceeds the number of times of writing “80” stored in the threshold A11, it is determined that there are a plurality of devices. Then, the SSD number “01” having the write count “85” is selected as the SSD number of the SSD 40 having the highest write count.

  When it is determined that there are not a plurality of SSDs 40 whose write count exceeds the threshold A11 (S105: NO), the write count monitoring unit 7 stores the threshold B12 stored in the SSD data copy threshold table 10 among the extracted write counts. It is determined whether or not there is an SSD 40 having a write count exceeding (S107).

  When it is determined that there is no SSD 40 whose write count exceeds the threshold B12 (S107: NO), the write count monitoring unit 7 determines that there is no SSD 40 that exceeds the threshold A11 at the above-described step S103 (S103: NO). Similarly, the process proceeds to step S104, the RAID configuration number to be checked is set to the next number (S104), the process proceeds to the process of step S100 described above, and the process described above is repeated.

  When it is determined that there is an SSD 40 whose write count exceeds the threshold B12 (S107: YES), the write count monitoring unit 7 selects the SSD number of the corresponding SSD 40 (S108).

  When the SSD number of the SSD 40 with the largest number of writes is selected among the SSDs 40 in the process of step S106 described above, or when the SSD number of the corresponding SSD 40 is selected in the process of step S108 described above, the write number monitoring unit 7 Selects the spare disk 50 with the smallest number of writes from among the SSDs (RAID configuration number “FF”) set in the spare disk 50 from the number-of-writes table 20 (S109).

  For example, in the example shown in FIG. 6, since the SSD number “0D”, SSD number “0E”, and SSD number “0F” are set as “FF” as the RAID configuration number, the spare disk 50 from which these are selected. Since the number of writes of the candidate spare disk 50 is “00”, “10”, and “15”, respectively, the SSD number “0D” with the smallest number of writes is the spare disk 50. Selected.

  Next, data is copied from the SSD 40 selected in step S106 or S108 to the spare disk 50 selected in step S109 (S110: first data writing means).

  More specifically, the write count monitoring unit 7 notifies the data copy instructing unit 8 that data copy is performed from the selected SSD 40 to the selected spare disk 50. Receiving the notification, the data copy instruction unit 8 instructs the disk control unit 6 to copy the data of the selected SSD 40 to the selected spare disk 50. Receiving the instruction, the disk controller 6 executes data copying. After the data copy is completed, information indicating the completion of the data copy is transmitted from the disk control unit 6 to the write count monitoring unit 7 via the data copy instruction unit 8. At this time, “5” is added to the write count of the spare disk 50.

  Next, after the data copy is completed, the write count monitoring unit 7 sets the copy source SSD 40 as a spare disk (S111: first reconfiguration unit). More specifically, the write count monitoring unit 7 sets the RAID configuration number of the copy source SSD 40 to “FF”, and the RAID configuration number of the selected spare disk 50 is set to the RAID of the copy source SSD. Set to the configuration number. As a result, the RAID configuration 60 is reconfigured.

  For example, the RAID configuration number 22 of the copy source SSD number “00” set as “00” as shown in FIG. 6 is set as “FF” as shown in FIG. Further, the RAID configuration number 22 of the SSD number “0D” of the selected spare disk 50 is set as “FF” as shown in FIG. 6 but is set to “00” as shown in FIG. Is done.

  Next, the write count monitoring unit 7 determines whether or not there is an SSD 40 to perform data copy (S112).

  When it is determined that there are SSDs 40 to perform data copy (S112: YES), in other words, when there are a plurality of SSDs 40 that are determined to exceed the threshold A11 in the process of step S105, all the SSDs 40 are stored. If the data copy process has not been performed, the write count monitoring unit 7 proceeds to step S106 described above and repeats the process described above.

  For example, in the example illustrated in FIG. 6, even when the process of copying the data of the SSD 40 with the SSD number “00” to the spare disk 50 with the SSD number “0D” is completed, the number of times the SSD 40 with the SSD number “01” is still written Since the value exceeds the threshold value A11, the process of copying the data of the SSD 40 with the SSD number “01” to the spare disk 50 with the SSD number “0E” with the smallest number of writes after the SSD number “0D” is performed. Thereafter, processing for reconfiguring the RAID configuration 60 is performed.

  On the other hand, when it is determined that there is no SSD 40 to perform data copy (S112: NO), the write count monitoring unit 7 proceeds to the above-described step S104 and sets the RAID configuration number to be checked to the next number (S104). Repeat the process described above.

  By performing the above processing, the disk array device 1 investigates the number of writes of each SSD 40 using the SSD write number table 20 when writing data, and as a result, the number of writes within the RAID configuration 60 is the threshold value A11. If only one SSD 40 exceeds the threshold B12, it is further determined whether or not the threshold B12 is exceeded. If the SSD 40 exceeds the threshold B12, the SSD 40 is automatically replaced with a spare disk 50 with the smallest number of writes. can do.

  Further, as a result of investigating the number of writes of the SSD 40, the disk array device 1 can automatically replace the plurality of SSDs 40 with a spare disk 50 having a smaller number of writes sequentially when there are a plurality of SSDs 40 exceeding the threshold A11. it can.

  Therefore, according to the disk array device 1, before the number of writes of the SSD 40 included in the RAID configuration 60 reaches the limit number, data is copied to the spare disk 50, and the SSD 40 whose number of writes approaches the limit number of writes. The redundancy of the RAID configuration 60 can be maintained by the automatic replacement.

  In addition, according to the disk array device 1, by determining whether to copy data to the spare disk 50 using the two threshold values A11 and B12, a plurality of SSDs 40 among the SSDs 40 constituting the RAID 60 can be simultaneously used. Reaching the write limit number can be prevented more reliably.

  In the first embodiment, when data is written to the SSD 40, as described with reference to steps S101 to S104, all the RAID configurations 60 are stored in the spare disk 50. Although the case where the process for performing the automatic exchange is executed has been described, the present invention is not limited to this. For example, when data is written to the SSD 40, only the RAID configuration 60 to which the SSD 40 belongs may be subjected to processing for automatic replacement with the spare disk 50.

(Second Embodiment)
Next, a second embodiment will be described. The first embodiment described above can prevent a plurality of SSDs 40 from simultaneously reaching the limit of writing, but when the disk array device 1 has a plurality of RAID configurations 60, When each SSD 40 included in the RAID configuration 60 is likely to reach the write limit number, it is necessary to prepare the same number of spare disks 50 as these. If the number of spare disks 50 is insufficient, the disk array device 1 may not be able to maintain the redundancy of the RAID configuration 60. In the second embodiment, a disk array device 1 that avoids this situation will be described.

  FIG. 9 is a diagram showing the configuration of the disk array device according to the second embodiment. The disk array device 1 is different from the disk array device 1 of the first embodiment described above in that the controller 2 has a write count scheduler 9 which is a second management unit, and a data copy threshold table. The difference is the number of threshold values stored in 10 ′, and the other parts are the same. Accordingly, the other components will be denoted by the same reference numerals as those of the disk array device 1 and will not be described in detail.

  As shown in FIG. 10, the data copy threshold table 10 ′ includes a threshold C13 that defines the number of writes to the SSD 40 and a threshold D14 that defines the difference in the number of writes between the SSDs 40 in addition to the above-described threshold A11 and threshold B12. Store. In the second embodiment, as shown in FIG. 12, the data copy threshold table 10 ′ stores “40” as the threshold C13 and “5” as the threshold D14. The threshold C13 and the threshold D14 can be changed from the management software installed in the host device 4 via the host control unit 5 in the same manner as the threshold A11 and the threshold B12.

  In the second embodiment, the threshold C13 and the threshold D14 are stored in the same data copy threshold table 10 ′ as the threshold A11 and the threshold B12, but are different from the threshold A11 and the threshold B12. It may be provided on a table. In the data copy threshold table 10 ′, the portion where the thresholds A11 and B12 are stored constitutes the first threshold storage unit, and the portion where the threshold C13 and threshold D14 are stored constitutes the second threshold storage unit. .

  The write count scheduler 9 is a management for managing the SSD 40 and the spare disk 50. The write count scheduler 9 performs processing for exchanging the SSD 40 whose write count has increased with the spare disk 50 based on the write count of each SSD 40 stored in the SSD write count table 20.

  Next, regarding the process of replacing the SSD 40 in which the number of writes in the disk array device 1 has increased with a predetermined timing, for example, the spare disk 50 periodically, the flowchart of FIG. 11 and the data copy threshold table 10 ′ of FIG. The description will be made with reference to the SSD write count table 20 shown in FIGS.

  First, the write count scheduler 9 selects a RAID configuration number from the SSD write count table 20 (S200).

  Next, the writing frequency scheduler 9 determines whether or not the selection is completed, more specifically, whether or not the RAID configuration number has been selected (S201). If it is determined that the selection of the RAID configuration number has been completed (S201: YES), in other words, if all the RAID configuration numbers have been selected and the processing described below has been completed, the write count scheduler 9 ends this processing. .

  On the other hand, when one RAID configuration number is selected (S201: YES), the write count scheduler 9 sets the write count for each SSD 40 having the same RAID configuration number as the selected RAID configuration number to the SSD write count table 20. (S202).

  For example, in the example shown in FIG. 13, when “01” is selected as the RAID configuration number, the write count scheduler 9 uses the SSD number “03”, SSD having the same RAID configuration number as the selected RAID configuration number. It is checked that the write count 23 of the number “04” is “41”, “45”.

  Next, the write count scheduler 9 determines whether or not there is an SSD 40 with the write count exceeding the threshold C13 stored in the SSD data copy threshold table 10 ′ among the checked write count 23 (S203: third). Judgment means).

  When it is determined that there is an SSD 40 whose write count exceeds the threshold C13 (S203: YES), the write count scheduler 9 determines whether there are a plurality of SSDs 40 that exceed the threshold C13 (S205: Fourth determination means) ).

  If it is determined in step S203 that there is no SSD 40 exceeding the threshold C13 (S203: NO), or if it is determined in step S204 that there are not a plurality of SSDs 40 exceeding the threshold C13 (S204: NO), the write count scheduler 9 Selects the RAID configuration number 22 to be checked as the next number (S204), proceeds to the process of step S200 described above, and repeats the process described above.

  On the other hand, when it is determined that there are a plurality of SSDs 40 whose write count exceeds the threshold C13 (S205: YES), the write count scheduler 9 indicates that the difference in the write count 23 between the SSDs 40 whose write count exceeds the threshold C13 is as described above. It is determined whether or not the threshold value D14 is below (S206).

  When it is determined that the difference between the write counts 23 is equal to or less than the threshold D14 (S206: YES), the write count scheduler 9 selects one SSD number 21 from the SSD 40 from which the write count is extracted (S207: second selection means) ).

  For example, in the example shown in FIG. 13, when “01” is selected as the RAID configuration number 22, “41” and “45” are checked as the write count 23 of the SSD 40 with the SSD numbers “03” and “04”. The The number of times of writing exceeds “40” defined as the threshold value C13, and “5” that is the difference between the number of times of writing is less than or equal to “5” defined as the threshold value D14. The SSD number “04” having a large number is selected.

  If it is determined that the difference between the write counts 23 is not less than or equal to the threshold D14 (S206: NO), the write count scheduler 9 sets the RAID configuration number 22 to be checked to the next number (S204) and repeats the above-described processing.

  When one SSD 40 is selected in step S207, the write count scheduler 9 selects one spare disk 50 from the SSD write count table 20 (S208).

  For example, in the example shown in FIG. 13, the SSD number “0F” has a smaller number of writes 23 than the two SSDs 40 with the SSD numbers “0E” and “0F” in which “FF” is set as the RAID configuration number 22. The SSD 40 is selected.

  Next, data is copied from the SSD 40 selected in step S207 to the spare disk 50 selected in step S208 (S209: second data writing means).

  Next, after the data copy is completed, the write count scheduler 9 sets the copy source SSD 40 as the spare disk 50 (S210: second reconfiguration means). As a result, the RAID configuration 60 is reconfigured.

  For example, in the example shown in FIG. 13, the RAID configuration number of the copy source SSD number “04” set as “01” as shown in FIG. 13 is changed to “FF” as shown in FIG. "Is set. Further, the RAID configuration number 22 of the SSD number “0F” of the selected spare disk 50 is set to “FF” as shown in FIG. 13, but is set to “01” as shown in FIG. Is done. As a result, the RAID configuration 60 is reconfigured.

  Next, the write count scheduler 9 sets the RAID configuration number 22 to be checked to the next number (S204), proceeds to the above-described step S200, and repeats the above-described processing.

  By repeating the processing in this manner, for example, in the example shown in FIG. 14, the processing described with reference to FIG. 11 described above is performed for each SSD 40 having the next RAID configuration number “02”. The SSD 40 having the RAID configuration number “02” has three SSD numbers “05”, “06”, and “07”. The number of times of writing is “60”, “60”, and “60”, respectively. is there. Since these all exceed the threshold C13, the difference between the SSDs 40 is calculated. Since this difference is not more than the threshold value D14 between any SSDs 40, one SSD 40, for example, the SSD 40 with the SSD number “05” is selected from these. For example, the SSD number “04” is selected as the spare disk 50.

  Next, data copy is executed in the same manner as the processing in step S209 described above. When the data copy is completed, for example, in the example shown in FIG. 14, the RAID configuration number of the copy source SSD number “05” is set to “02” as shown in FIG. As shown in FIG. 14, “FF” is set. Further, the RAID configuration number 22 of the SSD number “04” of the selected spare disk 50 that is set to “FF” as shown in FIG. 13 is set to “02” as shown in FIG. Is done. As a result, the RAID configuration 60 is reconfigured.

  According to the disk array device 2 of the second embodiment, the write count scheduler 9 periodically repeats the processing described with reference to FIG. 11, for example, to periodically write the SSDs 40 having the same RAID configuration number 22. It is possible to prevent the difference in the number of times from becoming the threshold value D41 or less. In other words, it is possible to prevent the writing times of the SSDs 40 in the same RAID configuration 60 from being equalized and prevent the SSDs 40 having the same RAID configuration number 22 from reaching the writing number limit at the same time.

  In addition, this invention is not limited to the above-mentioned embodiment, A various deformation | transformation is possible in the case of the implementation.

  A part or all of the above embodiment can be described as in the following supplementary notes, but is not limited thereto.

(Appendix 1)
A storage device that maintains data redundancy using a plurality of data storage devices for storing data,
Spare data storage device,
A first threshold that defines the number of writes to the data storage device and a second threshold that defines a number of writes that is greater than the first threshold and less than the write limit of the data storage device are stored. A first threshold value storage unit,
A write number storage unit for storing the number of data writes to each data storage device and the spare data storage device;
A first management unit for managing the data storage device and the spare data storage device;
With
The first management unit includes:
A first determination unit configured to determine whether or not the number of writes of the plurality of data storage devices exceeds the first threshold based on the number of writes stored in the write number storage unit when writing data; ,
A second determination unit that determines whether there are a plurality of data storage devices when the first determination unit determines that there is a data storage device that exceeds the first threshold;
A first selection unit that selects one data storage device from the plurality of data storage devices when the second determination unit determines that there are a plurality of data storage devices;
First data writing means for writing data stored in the data storage device selected by the first selection means into the spare data storage device;
First reconfiguring means for reconfiguring the configuration for maintaining the redundancy using a spare data storage device in which data is written by the first data writing means;
A storage apparatus comprising:

(Appendix 2)
The first management unit performs the first selection unit, the first data writing unit, and the first replaying unit until the second determination unit determines that there are no data storage devices. The storage apparatus according to claim 1, wherein the configuration unit is operated.

(Appendix 3)
A second threshold value storage unit that stores a third threshold value that defines a smaller number of times of writing than the first threshold value and a fourth threshold value that defines a difference in the number of times of writing between the data storage devices;
A second management unit for managing the data storage device and the spare data storage device;
With
The second management unit
Third determination means for determining whether or not the number of writes of the plurality of data storage devices exceeds the third threshold based on the number of writes stored in the write number storage unit at a predetermined timing;
Fourth determination means for determining whether or not there is a data storage device that exceeds the third threshold by the third determination means;
When the fourth determining means determines that there are a plurality of the data storage devices, it is determined whether or not the difference in the number of writes between the plurality of data storage devices is less than or equal to the fourth threshold, Second selection means for selecting one of the data storage devices determined to have a difference equal to or less than the fourth threshold;
Second data writing means for writing data stored in the data storage device selected by the second selection means into the spare data storage device;
Second reconfiguring means for reconfiguring a configuration for maintaining pre-redundancy using a spare data storage device in which data is written by the second data writing means;
The storage apparatus according to claim 1, further comprising:

(Appendix 4)
A data storage device replacement method for a storage device that maintains data redundancy using a plurality of data storage devices for storing data,
The storage device
Spare data storage device,
A first threshold that defines the number of writes to the data storage device and a second threshold that defines a number of writes that is greater than the first threshold and less than the write limit of the data storage device are stored. A first threshold value storage unit,
A write number storage unit for storing the number of data writes to each data storage device and the spare data storage device;
A first management unit for managing the data storage device and the spare data storage device;
It is equipped with
The data storage device exchange method is:
When writing data, determining whether or not the number of writes of a plurality of data storage devices exceeds the first threshold based on the number of writes stored in the write number storage unit;
Determining that there are a plurality of data storage devices when it is determined that there is a data storage device exceeding the first threshold; and
If it is determined that there are a plurality of the data storage devices, selecting one data storage device from the plurality of data storage devices;
Writing the data stored in the selected data storage device to the spare data storage device;
Reconfiguring the configuration to maintain the redundancy using a spare data storage device in which the data is written;
A data storage device replacement method for a storage device, comprising:

  The present invention can be widely applied to a storage device that can replace a data storage device that stores data and a data storage device replacement method for the storage device.

DESCRIPTION OF SYMBOLS 1 ... Disk array apparatus 2 ... Controller 3 ... Disk part 4 ... Host apparatus 5 ... Host control part 6 ... Disk control part 7 ... Write frequency monitoring part 8 ... Data copy instruction unit 9... Write count scheduler 10, 10 '... SSD data copy threshold table 20... SSD write count table 40.
50 ... Spare disk 60 ... RAID configuration

Claims (3)

A storage device having a plurality of configurations for maintaining data redundancy by using a plurality of data storage devices for storing data,
Spare data storage device,
A first threshold that defines the number of writes to the data storage device and a second threshold that defines a number of writes that is greater than the first threshold and less than the write limit of the data storage device are stored. A first threshold value storage unit,
A write number storage unit for storing the number of data writes to each data storage device and the spare data storage device;
A first management unit for managing the data storage device and the spare data storage device;
A second threshold value storage unit that stores a third threshold value that defines a smaller number of times of writing than the first threshold value and a fourth threshold value that defines a difference in the number of times of writing between the data storage devices;
A second management unit for managing the data storage device and the spare data storage device;
With
The first management unit includes:
A first determination unit configured to determine whether or not the number of writes of the plurality of data storage devices exceeds the first threshold based on the number of writes stored in the write number storage unit when writing data; ,
A second determination unit that determines whether there are a plurality of data storage devices when the first determination unit determines that there is a data storage device that exceeds the first threshold;
A first selection unit that selects one data storage device from the plurality of data storage devices when the second determination unit determines that there are a plurality of data storage devices;
A second threshold value judging means for judging whether or not the number of writes of the data storage device exceeds the second threshold value when it is judged by the second judgment means that there are not a plurality of data storage devices;
A data storage device selection unit for selecting the determined data storage device when the second determination unit determines that the second threshold value is exceeded;
A first data writing means for writing data stored in the data storage device selected by the first selection means or the data storage device selected by the data storage device selection means to the spare data storage device;
First reconfiguring means for reconfiguring the configuration for maintaining the redundancy using a spare data storage device in which data is written by the first data writing means;
The second management unit
Third determining means for periodically determining whether or not the number of writes of the plurality of data storage devices exceeds the third threshold based on the number of writes stored in the write number storage unit;
Fourth determination means for determining whether or not there are a plurality of data storage devices that exceed the third threshold by the third determination means;
When the fourth determining means determines that there are a plurality of the data storage devices, it is determined whether or not the difference in the number of writes between the plurality of data storage devices is less than or equal to the fourth threshold, Second selection means for selecting one of the data storage devices determined to have a difference equal to or less than the fourth threshold;
Second data writing means for writing data stored in the data storage device selected by the second selection means into the spare data storage device;
Second reconfiguring means for reconfiguring the configuration for maintaining the redundancy using a spare data storage device in which data is written by the second data writing means;
Exchange means for exchanging the data storage device in which data is written in the spare data storage device with a spare data storage device;
A storage apparatus comprising:   The first management unit performs the first selection unit, the first data writing unit, and the first replaying unit until the second determination unit determines that there are no data storage devices. The storage apparatus according to claim 1, wherein the configuration unit is operated. A data storage device replacement method for a storage device having a plurality of configurations for maintaining data redundancy using a plurality of data storage devices for storing data,
The storage device
Spare data storage device,
A first threshold that defines the number of writes to the data storage device and a second threshold that defines a number of writes that is greater than the first threshold and less than the write limit of the data storage device are stored. A first threshold value storage unit,
A write number storage unit for storing the number of data writes to each data storage device and the spare data storage device;
A first management unit for managing the data storage device and the spare data storage device;
A second threshold value storage unit that stores a third threshold value that defines a smaller number of times of writing than the first threshold value and a fourth threshold value that defines a difference in the number of times of writing between the data storage devices;
A second management unit for managing the data storage device and the spare data storage device;
It is equipped with
The first management unit
When writing data, determining whether or not the number of writes of a plurality of data storage devices exceeds the first threshold based on the number of writes stored in the write number storage unit;
Determining that there are a plurality of data storage devices when it is determined that there is a data storage device exceeding the first threshold; and
If it is determined that there are a plurality of the data storage devices, selecting one data storage device from the plurality of data storage devices;
If it is determined that there are not a plurality of the data storage devices, the step of determining whether or not the number of writes of the data storage device exceeds the second threshold;
If it is determined that the second threshold value is exceeded, the step of selecting the determined data storage device;
And writing the data stored in the selected data storage device in the data storage device for the spare,
Reconfiguring the configuration to maintain the redundancy using a spare data storage device in which the data is written;
Run
The second management unit
A step of periodically determining whether or not the number of writes of the plurality of data storage devices exceeds the third threshold based on the number of writes stored in the write number storage unit;
Determining whether or not there are a plurality of data storage devices exceeding the third threshold by the third determining means;
When it is determined that there are a plurality of the data storage devices, it is determined whether or not the difference in the number of writings between the plurality of data storage devices is equal to or less than the fourth threshold value, Selecting one of the data storage devices determined to be:
Writing the data stored in the selected data storage device to the spare data storage device;
Reconfiguring the configuration to maintain the redundancy using a spare data storage device in which the data is written;
Replacing the data storage device in which data is written in the spare data storage device with a spare data storage device;
A data storage device replacement method for a storage device, characterized in that:

Images