JP2012022645A - Data storage system and asynchronous replication method - Google Patents

Abstract

PROBLEM TO BE SOLVED: To surely provide order assurance of data update by judgment of a primary data storage device.SOLUTION: When writing data to a first storage medium is instructed by a host device 13-1, a cache memory managing unit of a primary data storage device 10-1 secures a cache area for storing designated data as write back data and a buffer area for transmitting the designated data to an auxiliary data storage device 10-2 in a first cache memory, and writes the data into each of them. A replication managing unit of the primary data storage device 10-1 requests unestablished write to the auxiliary data storage device 10-2 to write data stored in the buffer area to a second cache memory as unestablished write data, and requests establishing of the unestablished write data to the auxiliary data storage device 10-2 for establishing the unestablished write data already written in the second cache memory into write back data when the unestablished write data exceeds a predetermined volume.

Description

  Embodiments described herein relate generally to a data storage device and an asynchronous replication method.

  Conventionally, a primary data storage device (primary data storage device) placed at the primary site (primary site) and a secondary data storage device (secondary site) placed at a secondary site (secondary site) that is remote from the primary site Data storage system). In this type of data storage system, there is a demand to continue the business at the secondary site when the primary site is destroyed due to a disaster or the like for high reliability.

  For this reason, a copy of the data stored in the primary data storage device is stored in the secondary data storage device. In creating this replica, the data update in the secondary data storage device must be performed in the same order as the data update in the primary data storage device. That is, the data storage system is required to have an order guarantee function for guaranteeing the data update order between the primary data storage device and the secondary data storage device. The data storage device is also required to have a function for guaranteeing disk performance that does not depend on the distance between the primary site and the secondary site.

  Therefore, in order to satisfy the above-mentioned functional requirements necessary for high reliability, the data storage device has an asynchronous replication function for transferring data to the secondary site while completing data processing at the primary site, for example. It is common.

  However, in order to realize this asynchronous replication function, a dedicated buffer is provided in the primary data storage device and the secondary data storage device separately from the cache memory, or a dedicated relay transfer device is provided between the primary site and the secondary site. It is necessary to provide it. Further, there is a protocol overhead such as assigning a sequence number and interpreting the sequence number by the backup device.

JP 2003-167684 A

  It is possible to guarantee the order of data update by determining the data storage device at the primary site, eliminating the need for relay devices and dedicated large-capacity buffers, reducing the overhead due to the protocol, and the host device even during continuous writes to the same area It is an object to provide a data storage system and an asynchronous replication method that do not cause a decrease in response to the problem.

  The data storage system according to the present embodiment includes a first data storage device including a first storage medium for storing data, and a first control device that controls access to the first storage medium; A second storage medium for storing data and a second control device for controlling access to the second storage medium, and connected to the first data storage device via a data communication path A second data storage device, wherein the first control device stores a first cache memory for storing data to be read from or written to the first storage medium, and the first data storage device A first cache memory management means for managing access to the cache memory and the first and second storage media, and a copy of the data stored in the first storage medium is stored in the second storage medium Be done Replication management means for performing replication management with a specific replication state for operating as a local error, and the second control device stores data read or written to the second storage medium The first cache memory management means, when the data write from the external device to the first storage medium is designated in the specific replication state, the first cache memory management means A cache area for storing the designated data as write-back data to be written to the first storage medium, and the designated data is transmitted to the second data storage device. Undetermined write data prohibited from being written to the second storage medium And the designated data is written in the respective areas, and the replication management means stores the unconfirmed write data written in all the buffer areas in the second area. When an unconfirmed write for writing to the cache memory is requested to the second data storage device and the unconfirmed write data exceeds a set amount by requesting the unconfirmed write, or a predetermined timing When data has arrived, data that has already been written from the buffer area to the second cache memory as the data that has not yet been written is data that has been written to the second storage medium. The write data request is requested to the second data storage device.

The block diagram which shows the structure of the data storage system which concerns on this embodiment. 1 is a block diagram showing a schematic configuration of a data storage device according to an embodiment. The block diagram which mainly shows the module structure of the control apparatus shown by FIG. The block diagram which shows the example of a data structure of the cache directory entry applied in this embodiment. The figure which shows the data structure example of the replication management table and I / O management list which are applied by this embodiment. 6 is a flowchart showing a processing procedure in the data storage device when a write process is requested from an external device in the present embodiment. 6 is a flowchart showing a procedure of an unconfirmed write command process executed on the primary data storage device side in the present embodiment. 6 is a flowchart showing a procedure of an unconfirmed write command process executed on the primary data storage device side in the present embodiment. 6 is a flowchart showing the procedure of an indefinite write confirmation command process executed on the primary data storage device side in the present embodiment. 9 is a flowchart showing the procedure of an indeterminate write confirmation command process executed on the secondary data storage device side in the present embodiment. 6 is a flowchart showing a detailed procedure of processing when a cache block is secured in the present embodiment.

  Hereinafter, the present embodiment will be described with reference to the drawings.

  FIG. 1 shows a configuration of a data storage system 100 according to the present embodiment. The data storage system 100 includes a primary data storage device (first data storage device) 10-1 disposed at the primary site 100-1 and a secondary data storage device (second data) disposed at the secondary site 100-2. Storage device) 10-2. The primary site 100-1 and the secondary site 100-2 exist, for example, at positions separated from each other. That is, the secondary site 100-2 exists at a remote location from the primary site 100-1.

  In the primary site 100-1, the primary data storage device 10-1 is connected to a host device 13-1 that is a host device via a data communication path 11-1 including a connection device 12-1. In the secondary site 100-2, the secondary data storage device 10-2 is connected to the host device 13-2 via the data communication path 11-2 including the connection device 12-2. The data communication path 11-1 and the data communication path 11-2 are, for example, Fiber Channel, iSCSI, or SCSI. The primary data storage device 10-1 may be connected to a plurality of host devices including the host device 13-1 via the data communication path 11-1. Similarly, the secondary data storage device 10-2 may be connected to a plurality of host devices including the host device 13-2 via the data communication path 11-2. The host device 13-1 is a computer that uses the primary data storage device 10-1, and the host device 13-2 is a computer that uses the secondary data storage device 10-2.

  The connection device 12-1 at the primary site 100-1 and the connection device 12-2 at the secondary site 100-2 are connected via the network 14. The connection devices 12-1 and 12-2 are, for example, fabric switches. The network 14 is, for example, a wide area network. The connection devices 12-1 and 12-2 are connected to the network 14 via a Fiber Channel-Internet Protocol (FCP) converter (not shown), for example.

  FIG. 2 is a block diagram showing a schematic configuration of the data storage device 10-i (i = 1, 2) shown in FIG.

  The data storage device 10-i includes a control unit 20-i and a storage medium 80-i. The control unit 20-i is provided between the host device 13-i and the storage medium 80-i connected via the data communication path 11-i. The storage medium 80-i is, for example, a logical disk, and includes a hard disk drive (HDD), an SSD (Solid State Drive), or the like. Hereinafter, the storage medium 80-i is referred to as a logical disk (LDISK) 80-i. In the present embodiment, in order to simplify the description, it is assumed that the data storage device 10-i has one LDISK 80-i. However, the data storage device 10-i may have a plurality of LDISKs.

  The control unit 20-i includes a host I / F unit (HOST I / F) 61-i, a CPU 21-i, a program memory 31-i, a flash memory 41-i, a cache memory 51-i, and an HDD I / F unit. (HDD I / F) 71-i.

  The host I / F unit 61-i controls communication with an externally connected device. That is, the host I / F unit 61-i manages communication on the data communication path 11-i side. The HDD I / F unit 71-i manages communication on the LDISK 80-i side.

  The CPU 21-i executes necessary processing in the control unit 20-i, and the flash memory 41-i is a nonvolatile memory in which various programs are stored. The program memory 31-i stores a data area for storing a program loaded from the flash memory 41-i which is a nonvolatile memory, data used by the CPU 21-i, and the like. Assume that the asynchronous replication technique applied in the present embodiment is realized by the CPU 21-i reading and executing a program loaded in the program memory 31-i and stored therein. In the program memory 31-i, in addition to an area for storing the above-described program, an area for storing data used by the CPU 21-i is also secured.

  The cache memory 51-i is an input / output issued to the LDISK 80-i in the data storage device 10-i from the host device 13-i or another data storage device connected via the data communication path 11-i. In a request (I / O request), data to be read or written is temporarily stored.

  The cache memory 51-i is managed by being divided into certain logical units. The data at the storage location can be stored in the cache memory 51-i by freely corresponding to the storage location in the LDISK 80-i in this divided unit. This divided unit is called a cache block. Each cache block is managed, for example, by memory mapping using a set associative method.

  In the data storage device 10-i, a write process in response to an input request from an external device such as the host device 13-i is performed as follows. First, when the input data (write data) specified by the input request is entered into the cache memory 51-i, the requesting host device 13-i is notified of the completion of the write process. Thereafter, actual data writing from the cache memory 51-i to the LDISK 80-i is executed.

  On the other hand, a read process for an output request from the host device 13-i is performed as follows. First, it is determined whether or not the corresponding data is entered (cached) in the cache memory 51-i. If the entry is entered, the data is transferred from the cache memory 51-i to the host via the data communication path 11-i. Returned to device 13-i. On the other hand, if the corresponding data is not entered in the cache memory 51-i, the data is read from the LDISK 80-i to the cache memory 51-i. Then, the read data is returned to the requesting host apparatus 13-i via the data communication path 11-i.

  FIG. 3 is a block diagram mainly showing a module configuration realized, for example, by the CPU 21-i reading and executing a program stored in the program memory 31-i of the control unit 20-i shown in FIG.

  The host I / F control unit (host I / F control unit) 210-i is in charge of interface processing between the data storage device 10-i and the host device 13-i. In particular, the host I / F control unit 210-1 of the primary data storage device 10-1 is also responsible for interface processing with other data storage devices (sub data storage device 10-2). This interface processing includes input / output processing. That is, the host I / F control unit 210-i receives a command sent from the communication port management unit 270-i, which will be described later, using, for example, a CDB (Command Descriptor Block: command description block), and sends the command to other data. By transmitting to the storage device, input / output processing with another data storage device is performed. In the present embodiment, there is a normal write command as a command sent from the host device 13-1 to the primary data storage device 10-1 using the CDB. Commands sent from the primary data storage device 10-1 to the secondary data storage device 10-2 using the CDB include an unconfirmed write command and an unconfirmed write confirmation command. These commands will be described later.

  The I / O management unit (input / output management unit) 220-i decodes the CDB received by the host I / F control unit 210-i. In particular, the I / O management unit 220-2 of the secondary data storage device 10-2 makes an unconfirmed write command or an unconfirmed command to the cache memory management unit 230-2 in response to the unconfirmed write command or the unconfirmed write confirmation command. I / O access management (input / output access management) is performed by requesting a confirmed write confirmation command.

  The cache memory management unit 230-i receives a request from the I / O management unit 220-i and based on the cache directory 232-i stored in the cache directory storage unit 231-i (see FIG. I / O access management in 2). The data structure of the cache directory 232-i will be described later.

  In this embodiment, the LDISK 80-i includes a plurality of disk arrays, for example, two disk arrays 800-i having a RAID (Redundant Arrays of Independent Disks, Redundant Arrays of Inexpensive Disks) configuration as shown in FIG. Shall. That is, in the present embodiment, the data storage device 10-i is a disk array device.

  The disk array 800-i does not always correspond to the LDISK 80-i on a one-to-one basis. For example, a part of the disk array 800-i may be assigned to a part of the LDISK 80-i, and another part of the disk array 800-i may be assigned to a part of another LDISK.

  The RAID controller 240-i manages each disk array 800-i as a set of physical disks. The RAID control unit 240-i controls the transfer of disk data to and from the disk array 800-i that is the target of disk transfer in the LDISK 80-i in response to a request from the cache memory management unit 230-i. The HDD I / F control unit (HDD I / F control unit) 250-i responds to a request from the RAID control unit 240-i and includes one or more target disks to be transferred in the disk array 800-i. Controls the transfer of disk data to and from the physical disk.

  Note that the LDISK 80-i does not necessarily have to be composed of a disk array, and therefore the data storage device 10-i may not be a disk array device. Furthermore, it is possible to use another storage medium such as a physical disk in place of LDISK80-i.

  The replication management unit 260-i includes a replication management table 262-i stored in the replication management data storage unit 261-i and an I / O management list 264- stored in the I / O management list storage unit 263-i. Manage and control replication based on i. The data structure of the replication management table 262-i and the I / O management list 264-i will be described later.

  The communication port management unit 270-i manages an access port for communication with other data storage devices.

  As described above, a logical unit for managing the cache memory 51-i is called a cache block. A management data structure for managing the cache block in a one-to-one correspondence with the cache block is called a cache directory entry. The cache directory 232-i is a set of cache directory entries.

  FIG. 4 shows an example of the data structure of the cache directory. In this embodiment, the cache directory entry data (cache directory data) includes a logical disk number, a logical address, a status flag, a read cache bitmap, a write-back bitmap (first variable), and an indeterminate write bitmap ( Second variable).

  The logical disk number indicates the logical disk to which the corresponding cache block is allocated, and the logical address indicates the start address of the area (logical block area) in the logical disk to which the corresponding cache block is allocated. The status flag indicates the status of the corresponding cache block, for example, whether or not the cache block is in use.

  The read cache bitmap, the write back bitmap, and the indeterminate write bitmap indicate the position of valid data in the corresponding cache block in bits in units smaller than the block, for example, in sectors. Valid data refers to read cache data in the corresponding cache block in the read cache bitmap, and write back data (so-called so-called write-back data to be written to the logical disk indicated by the logical disk number in the corresponding cache block in the write-back bitmap. Dirty data). Further, the unconfirmed write bitmap indicates unconfirmed write data in the corresponding cache block. Unlike the write-back data, the indeterminate write data is data that should not be written to the logical disk, that is, data that is prohibited from being written to the logical disk. When unconfirmed data is confirmed, it is treated as write-back data.

  In this embodiment, there are three replication states: a synchronization (SYNC) state, a copy (COPY) state, and a split (SPLIT) state. The initial state immediately after creation of replication is SPLIT. The SPLIT state refers to a state in which the LDISK 80-1 (primary logical disk) of the primary data storage device 10-1 and the LDISK 80-2 (secondary logical disk) of the secondary data storage device 10-2 are logically disconnected. That is, in the SPLIT state, the primary data storage device 10-1 and the secondary data storage device 10-2 function as independent data storage devices.

  In the SPLIT state, for example, when a synchronization request is given from the host device 13-1 to the primary data storage device 10-1, the state changes from the SPLIT state to the COPY state. In this COPY state, a COPY process is performed in which data is read from the LDISK 80-1 and the read data is written to the LDISK 80-2. In this COPY process, a normal write is requested from the primary data storage device 10-1 to the secondary data storage device 10-2. The processing in the secondary data storage device 10-2 at this time is the same as the processing in the case where the write request is not requested in the data storage device when the write processing is requested from an external device shown in FIG. It is the same. That is, the COPY process is performed on the secondary logical disk by the destaging process executed at the timing of the secondary data storage device 10-2 as in the normal write. When the COPY process is completed, the state transits to the SYNC state. These states are controlled by the replication management unit 260-i.

  FIG. 5 shows an example of the data structure of the replication management table 262-i and the I / O management list 264-i used for replication management and control by the replication management unit 260-i. The replication management table 262-i holds a primary logical disk number, a secondary logical disk number, replication state information, replication cycle information, fixed cycle information, transmittable data amount information, transmitted data amount information, and a fixed flag.

  The primary logical disk number indicates the number of the primary logical disk that is the replication source (replication master) in the primary data storage device 10-1. The secondary logical disk number indicates the number of the secondary logical disk that is the replication destination (replication sub) in the secondary data storage device 10-2. The replication state information indicates one of the three replication states described above. In the present embodiment, the LDISK 80-1 (first storage medium) and the LDISK 80-2 (second storage medium) make a pair to form a replication pair.

  The replication cycle information performs a transfer process for transferring write data corresponding to an I / O request described in a buffering I / O list described later from the primary data storage device 10-1 to the secondary data storage device 10-2. Indicates the period. The fixed cycle information indicates a cycle for determining the undefined write data. The transmittable data amount information indicates the amount of data that can be transmitted as unconfirmed data from the primary data storage device 10-1 to the secondary data storage device 10-2 within one cycle indicated by the fixed cycle information. The transmittable data amount is set, for example, to an amount that allows an area in the cache memory 51-2 to be allocated for unconfirmed data to be sent to the secondary data storage device 10-2 within one cycle. The transmitted data amount information indicates the transmitted data amount already transmitted as unconfirmed data from the primary data storage device 10-1 to the secondary data storage device 10-2. The confirmation flag indicates whether or not an unconfirmed write confirmation command is being executed.

The I / O management list 264-i includes an execution I / O list 264a-i, a pending I / O list 264b-i, and a buffering I / O list 264c-i. The execution I / O list 264a-i has a queue-type list structure that holds execution I / O requests in order of request. The pending I / O list 264b-i has a queue-type list structure that holds pending I / O requests in order of request. An execution I / O request refers to an I / O request that can be executed at the present time. A pending I / O request refers to an I / O request that cannot be executed at this time. The buffering I / O list 264c-i has a queue-type list structure that holds buffering I / O requests in order of request. The buffering I / O request refers to an I / O request to be transmitted to the secondary data storage device as unconfirmed write data.

  Next, with respect to the operation of the present embodiment, when the replication state is the SYNC state, the primary data storage device when a CDB including a normal write command is transmitted from the host device 13-1 to the primary data storage device 10-1. The operation of 10-1 and the sub data storage device 10-2 will be described as an example with reference to the flowchart of FIG.

  Now, it is assumed that a CDB including a normal write command is transmitted from the host device 13-1 to the primary data storage device 10-1 via the data communication path 11-1. The normal write command includes access information including a logical disk number, a start address, and a size. The primary logical disk number in this access information indicates the write destination LDISK 80-1 in the primary data storage device 10-1. The start address in the access information indicates the address of the start position of the storage area (write access range) in the LDISK 80-1 to which data is to be written, and the size in the access information indicates the size (transfer size) of this storage area. Show.

  The CDB transmitted from the host device 13-1 is received by the host I / F control unit 210-1, and passed to the I / O management unit 220-1. The I / O management unit 220-1 decodes the delivered CDB (step S1). In step S1, when the CDB includes a normal write command as in this embodiment, the I / O management unit 220-1 normally sends an I / O request for write processing to the cache memory management unit 230-1. Send a write request. The normal write request is an I / O request for normal write processing, and inherits the access information included in the normal write command.

  Next, the cache memory management unit 230-1 determines whether the LDISK 80-1 indicated by the logical disk number in the access information included in the I / O request is a replication master (step S2).

  When it is a replication master as in the present embodiment (Yes in step S2), the cache memory management unit 230-1 receives an I / O request for CDB write processing transmitted from the I / O management unit 220-1 ( When a normal write request is received, a necessary cache block in the cache memory 51-1 (first cache memory) and a buffer having the same capacity as the cache block are secured based on this I / O request. Then, the write data necessary for the write process specified by the I / O request is received and stored in the cache block and the buffer secured in step S3 (step S5). Then, a flag indicating that the cache block is in use and a flag indicating that the buffer is reserved are set in the status flag included in the cache directory entry of the cache directory 232-1. The secured buffer is used to transfer write data to the sub data storage device 10-2.

  Next, the cache memory management unit 230-1 determines whether the I / O request received from the I / O management unit 220-1 is an unconfirmed write request (step S7). If it is not an indefinite write request as in the present embodiment (No in step S7), the received write data is entered in a secured cache block in the cache memory 51-1 (step S8). In this step S8, the cache memory management unit 230-1 corresponds to the secured cache block with the write access range indicated by the access information included in the normal write request received from the I / O management unit 220-1. This is reflected in the write-back bitmap included in the cache directory entry of the cache directory 232-1. That is, the cache memory management unit 230-1 sets the bit corresponding to the write access range designated by the normal write request in the write-back bitmap corresponding to the secured cache block, for example, “1”.

  The flowchart shown in FIG. 6 is executed in common by the primary data storage device 10-1 and the secondary data storage device 10-2. However, in this embodiment, the write command included in the CDB transmitted from the host device 13-1 to the primary data storage device 10-1 is limited to the normal write command. Therefore, in the primary data storage device 10-1, step S7 is not necessarily required, and step S8 may be executed after step S5 or step 6.

  Next, the cache memory management unit 230-1 determines whether the LDISK 80-1 indicated by the logical disk number in the access information included in the I / O request is a replication master (step S10). When it is a replication master as in the present embodiment (Yes in step S10), the cache memory management unit 230-1 sends an I / O request for replication management to the replication management unit 260-1. This I / O request includes access information composed of a logical disk number, a start address, and a size, like the normal write request.

  When receiving an I / O request from the cache memory management unit 230-1, the replication management unit 260-1 refers to the pending I / O list 264b-1 of the I / O management list 264-1. Then, the replication management unit 260-1 determines whether there is an I / O request in the pending I / O list 264b-1 (step S13).

  If there is an I / O request in the pending I / O list 264b-1 (Yes in step S13), the data update order is guaranteed between the primary data storage device 10-1 and the secondary data storage device 10-2. This means that the I / O request received from the cache memory management unit 230-1 this time (the corresponding unconfirmed write request) cannot be immediately transmitted from the primary data storage device 10-1 to the secondary data storage device 10-2. To do.

  Therefore, when the determination in step S13 is Yes, the replication management unit 260-1 adds the I / O request received from the cache memory management unit 230-1 to the tail of the pending I / O list 264b-1 (step S13). S14). In step S14, the replication management unit 260-1 starts processing the unconfirmed write confirmation command only when the process branches from step S18 described later. This is because the processing has already been started at the time of execution of the first I / O connected to the pending I / O list 264b-1.

  Next, as a response to the normal write request from the host device 13-1, the replication management unit 260-1 notifies the host device 13-1 of status information indicating write completion (step S15), and releases the secured cache block. Is performed (step S16). Specifically, the flag indicating that the cache block set in the status flag included in the cache directory entry of the cache directory 232-1 when the cache block is secured is cleared. Then, the replication management unit 260-1 enters a state of waiting for the completion of execution of the unconfirmed write confirmation command to be notified from the secondary data storage device 10-2 (step S17). If the execution of the unconfirmed write confirmation command is successful, the process is resumed from step S18 described later. If execution of the unconfirmed write confirmation command fails, it is completed as an error. The processing of this unconfirmed write confirmation command will be described later.

  On the other hand, when the determination in step S13 is No, the replication management unit 260-1 determines the current transmitted data based on the transmitted data amount information and the transmittable data amount information held in the replication management table 262-1. Check the amount and the amount of data that can be sent. Then, the replication management unit 260-1 adds “the amount of transmitted data + the amount of received data” obtained by adding the amount of data received this time (that is, the amount of data to be transmitted to the secondary data storage device 10-2) to the amount of transmitted data. Is determined to exceed the transmittable data amount (step S18).

  If “transmitted data amount + received data amount” exceeds the transmittable data amount (Yes in step S18), it means that the data received this time cannot be transmitted to the secondary data storage device 10-2. Therefore, when the determination in step S18 is Yes, the replication management unit 260-1 executes step S14 and starts processing the unconfirmed write confirmation command.

  On the other hand, when the determination in step S18 is No, the replication management unit 260-1 adds the I / O request received from the cache memory management unit 230-1 to the end of the buffering I / O list 264c-1. (Step S19). As a response to the normal write request from the host device 13-1, the replication management unit 260-1 notifies the host device 13-1 of status information indicating write completion (step S20), and releases the secured cache block. (Step S21). Thereafter, the replication management unit 260-1 waits for a write data transfer process from the primary data storage device 10-1 to the secondary data storage device 10-2.

  The above-described write data transfer processing is executed when the replication cycle (timing) indicated by the replication cycle information held in the replication management table 262-1 has arrived. This replication cycle will be described.

  The replication management unit 260-1 holds a timer in the replication management table 262-1 when the first normal write request is executed, that is, when normal write is completed when the amount of transmitted data is “0”. Set to the time that represents the replication cycle indicated by the replication cycle information. Then, the replication management unit 260-1 executes a write data transfer process when this timer times out. The timer is reset when the write data transfer process is completed.

  When the timer setting condition is satisfied, the replication management unit 260-1 resets this timer based on the replication cycle information. As a result, in the present embodiment, the write data transfer process by the unconfirmed write command is executed in the replication cycle indicated by the replication cycle information. The above-mentioned indeterminate write command processing is performed not only when the replication cycle (timing) has arrived, but also when the amount of I / O requests in the buffering I / O list exceeds a preset threshold value, It is also possible to perform the processing when the secured buffer data amount exceeds a preset ratio with respect to the possible data amount. It is also possible to execute by using the execution I / O list element as a trigger.

  A periodic process that is an operation of the primary data storage device 10-1 when the replication period comes will be described with reference to FIGS.

  First, it is determined whether or not the unconfirmed write confirmation command is being executed based on the confirmation flag of the replication management table 262-1 shown in FIG. 5 (step S31). If the unconfirmed write confirmation command is being executed (No in step S31), the process is not performed and the process waits until the next replication cycle comes. If the unconfirmed write confirmation command is not being executed (Yes in step S31), it is determined whether or not there is an I / O request in the execution I / O list 264a-1.

  When there is an I / O request in the execution I / O list 264a-i (No in step S32), the same processing as in the case where No in step S31 is performed is performed. When there is no I / O request in the execution I / O list 264a-1 (Yes in Step S32), it is determined whether or not there is an I / O request in the buffering I / O list 264c-1 (Step S33). .

  When there is no I / O request in the buffering I / O list 264c-1 (No in Step S33), the same processing as that in the case where Step S31 and Step S32 are No is performed. If there is an I / O request in the buffering I / O list 264c-1 (Yes in step S33), the write data that can be simultaneously transferred to the secondary data storage device 10-2 is determined.

  First, it is determined whether or not a plurality of I / O requests for the same area are stacked in the buffering I / O list 264c-1 (step S34).

  When a plurality of I / O requests for the same area are stacked in the buffering I / O list 264c-1 (No in step S34), only the last I / O request in the buffering I / O list 264c-1 is stored. And the other buffers are released to complete the I / O request (step S35). Since the buffering I / O list is in a queue format and is connected in order from the top, the order does not change.

  When a plurality of I / O requests for the same area are not stacked in the buffering I / O list 264c-1 (Yes in step S34), a plurality of write requests whose areas overlap in the buffering I / O list 264c-1 It is determined whether or not there exists (step S36).

  If there are no multiple I / O requests whose areas overlap in the buffering I / O list 264c-1 (Yes in step S36), all the I / O requests in the buffering I / O list 264c-1 are executed. Move to the O list 264a-1 (step S37). If there is an I / O request with overlapping areas in the buffering I / O list 264c-1 (No in step S36), the first overlapping area from the beginning of the buffering I / O list 264c-1 The I / O request up to one before the / O request, that is, the I / O request before the occurrence of the overlap of the areas is moved to the execution I / O list 264a-1 (step S38).

  Thereafter, the communication port management unit 270-1 issues an unconfirmed write request to the secondary data storage device 10-2 for the I / O request of the execution I / O list 264a-1 (step S39). In step S39, the unconfirmed write request transmitted to the secondary data storage device 10-2 is decoded and executed by the I / O management unit 220-2 of the secondary data storage device 10-2.

  That is, the buffering I / O request that is an I / O request included in the buffering I / O list 264c-1 is an I / O that can be executed among I / O requests requested from an external device. Refers to the request. The execution I / O request refers to a buffering I / O request excluding I / O requests having overlapping areas.

  Next, the processing of the secondary data storage device 10-2 that has received the unconfirmed write command from the primary data storage device 10-1 will be described with reference to FIG.

  In step S39 in FIG. 7, the replication manager 260-1 issues an indeterminate write command corresponding to the I / O request added to the buffering I / O list 264c-1 to the communication port manager 270-1. Required. Then, the communication port management unit 270-1 transmits the CDB including the unconfirmed write command to the secondary data storage device 10-2. Then, the replication management unit 260-1 waits for a response from the secondary data storage device 10-2 to the unconfirmed write command.

  Then, the CDB transmitted to the secondary data storage device 10-2 in step S39 includes an unconfirmed write command. This unconfirmed write command includes access information composed of a logical disk number, a start address, and a size. The logical disk number is a secondary logical disk number stored in the replication management table 262-1 in association with the primary logical disk number, and indicates the write destination LDISK 80-2 of the secondary data storage device 10-2.

  The CDB transmitted to the secondary data storage device 10-2 is received by the host I / F control unit 210-2 of the control device 20-2 (second control device) and transferred to the I / O management unit 220-2. It is. The I / O management unit 220-2 decodes the delivered CDB (step S1). In step S1, when the CDB includes an unconfirmed write command, the I / O management unit 220-2 sends an unconfirmed write request as an I / O request for write processing to the cache memory management unit 230-2. To do. The indeterminate write request is an I / O request for indeterminate write processing, and inherits the access information included in the indeterminate write command.

  When the cache memory management unit 230-2 receives an I / O request for write processing (here, an indefinite write request) from the I / O management unit 220-2, the cache memory management unit 230-2 performs cache memory processing based on the I / O request. A necessary cache block is secured in 51-2 (second cache memory) (step S4), and the write data necessary for the write process specified by the I / O request is received in the cache block secured in step S4. (Step S6). Then, a flag indicating that the cache block is in use is set in the status flag included in the cache directory entry of the cache directory 232-1. Here, since the CDB is transmitted to the secondary data storage device 10-2, step S4 is executed after step S1.

  Next, the cache memory management unit 230-2 determines whether the received I / O request is an unconfirmed write request (step S7). In the case of an unconfirmed write request as in the present embodiment (Yes in step S7), the received write data is entered in a secured cache block in the cache memory 51-2 (step S9). In step S9, the cache memory management unit 230-2 includes the write access range indicated by the access information included in the unconfirmed write request in the cache directory entry of the cache directory 232-2 corresponding to the secured cache block. This is reflected in the undefined write bitmap. That is, the cache memory management unit 230-2 sets the bit corresponding to the write access range designated by the unconfirmed write request in the unconfirmed write bitmap corresponding to the secured cache block, for example, “1”.

  Next, the cache memory management unit 230-2 determines whether the LDISK 80-2 indicated by the logical disk number in the access information included in the I / O request is a replication master (step S10). Here, since it is not a replication master (No in step S10), the cache memory management unit 230-2 displays status information indicating completion of unconfirmed write as primary data as a response to the unconfirmed write request from the primary data storage device 10-1. The storage device 10-1 is notified (step S11), and the secured cache block is released (step S12).

  Here, the processing of the primary data storage device 10-1 when receiving status information indicating completion of indefinite write will be described with reference to FIG.

  As a response to the unconfirmed write request from the primary data storage device 10-1, status information indicating write completion is notified from the secondary data storage device 10-2 to the primary data storage device 10-1 (step S23). Then, the replication management unit 260-1 determines whether or not the indeterminate write has succeeded based on the status information (step S24).

  If the indefinite write has succeeded (Yes in step S24), the replication management unit 260-1 changes the transmitted data amount information held in the replication management table 262-1 to the current transmitted data amount. Update is performed to indicate a value obtained by adding the amount of data received this time (the amount of data transmitted to the sub data storage device 10-2) (step S26). Next, the replication management unit 260-1 deletes the I / O request corresponding to the successful unconfirmed write from the execution I / O list 264a-1 (Step S27), and releases the secured buffer (Step S28). ). Specifically, the flag indicating that the buffer is being secured, which is set in the status flag included in the cache directory entry of the cache directory 232-1 when the buffer is secured, is cleared. Thereby, the processing of the I / O request in the primary data storage device 10-1 is completed (step S29).

  On the other hand, if the indefinite write has failed (No in step S24), the replication management unit 260-1 changes the replication state from the SYNC state to the SPLIT state (step S25). That is, the replication management unit 260-1 updates the replication state information held in the replication management table 262-1 so as to indicate the SPLIT state. Then, the replication management unit 260-1 proceeds to step S36. In step S36, the replication management unit 260-1 deletes the I / O request corresponding to the failed indefinite write from the execution I / O list 264a-1 (step S27), and releases the secured buffer (step S27). Step S28). Thereby, the processing of the I / O request in the primary data storage device 10-1 is completed (step S29).

  Next, processing of the unconfirmed write confirmation command in the primary data storage device 10-1 executed following step S14 will be described with reference to the flowchart of FIG.

  First, the replication management unit 260-1 of the primary data storage device 10-1 refers to the execution I / O list 264a-1 and determines whether there is an I / O request in the execution I / O list 264a-1 ( Step S61). If there is an I / O request in the execution I / O list 264a-1 (Yes in step S61), the replication management unit 260-1 waits for completion of the execution of the I / O request (step 62).

  On the other hand, if there is no I / O request in the execution I / O list 264a-1, or if there is no I / O request in the execution I / O list 264a-1 (No in step S61), the replication management unit 260-1 requests the communication port management unit 270-1 to issue an unconfirmed write confirmation command (step S63). Then, the communication port management unit 270-1 transmits the CDB including the unconfirmed write confirmation command to the secondary data storage device 10-2, and transmits the CDB including the unconfirmed write confirmation command to the secondary data storage device 10-2. Is set in the confirmation flag of the replication management table 262-1. The unconfirmed write confirmation command specifies that unconfirmed data written to the cache memory 51-2 is confirmed as write-back data in response to an unconfirmed write request from the primary data storage device 10-1. The unconfirmed write confirmation command includes a logical disk number indicating LDISK 80-2 to which the confirmed data is to be written. As described above, in this embodiment, when there is an I / O request in the execution I / O list 264a-1, the CDB including the unconfirmed write confirmation command is stored in the positive data after waiting for completion of execution of all the I / O requests. The data is transmitted from the device 10-1 to the sub data storage device 10-2.

  When the CDB including the unconfirmed write confirmation command is transmitted to the secondary data storage device 10-2, the replication management unit 260-1 waits for a response from the secondary data storage device 10-2 to the unconfirmed write confirmation command ( FIG. 6 step S17). When the replication management unit 260-1 receives the status information from the secondary data storage device 10-2 in response to the unconfirmed write confirmation command, the replication management unit 260-1 determines whether the unconfirmed write confirmation has succeeded based on the information (step S64).

  If the unconfirmed write confirmation is successful (Yes in step S64), the replication management unit 260-1 initializes the transmitted data amount information held in the replication management table 262-1 to “0”. . Then, the replication management unit 260-1 removes the I / O requests connected to the pending I / O list 264b-1 in order from the top, and restarts the process from step S18 in the flowchart of FIG. 6 (step S65). However, transfer of status information to the host device 13-1 regarding the I / O request removed from the pending I / O list 264b-1 (step S11 or S20 in FIG. 6), the I / O request is transferred to the pending I / O list. Since it has already been performed when it is added to the O list 264b-1, it is not executed this time.

  On the other hand, if the unconfirmed write confirmation has failed (No in step S64), the replication management unit 260-1 indicates the replication state information held in the replication management table 262-1 to indicate the SPLIT state. Update (step S66). That is, the replication manager 260-1 changes the replication state from the SYNC state to the SPLIT state. Then, the replication management unit 260-1 completes the I / O request waiting in the pending I / O list 264b-1 as an error (step S67). At this time, data transfer to the secondary data storage device 10-2 is not performed.

  The above-described processing of the unconfirmed write confirmation command is performed not only when the determination condition of step S13 in the flowchart of FIG. 6 is satisfied, but also the confirmation period (timing) indicated by the confirmation period information held in the replication management table 262-1. It is also executed when. This fixed cycle will be described.

  The replication management unit 260-1 holds a timer in the replication management table 262-1 when the first unconfirmed write request is executed, that is, when the unconfirmed write is completed with the transmitted data amount being "0". It is set to a time representing the fixed cycle indicated by the fixed cycle information. Even when this timer times out, the replication management unit 260-1 executes the unconfirmed write confirmation command processing in the same manner as when the determination condition in step S13 in the flowchart of FIG. 6 is satisfied. The timer is reset when the unconfirmed write confirmation command started in step S14 is completed.

  When the timer setting condition is satisfied, the replication management unit 260-1 resets the timer based on the fixed cycle information. As a result, in this embodiment, the unconfirmed write confirmation command process is executed not only when the determination condition of step S13 is satisfied but also in the confirmation period indicated by the confirmation period information.

  Next, the processing of the unconfirmed write confirmation command on the secondary data storage device 10-2 side will be described with reference to FIG.

Now, the CDB including the unconfirmed write confirmation command transmitted from the primary data storage device 10-1 to the secondary data storage device 10-2 is received by the host I / F control unit 210-2 and received by the I / O management unit 220. Suppose it was passed to -2. When the CDB includes an unconfirmed write confirmation command, the I / O management unit 220-2 sends an unconfirmed write confirmation request as an I / O request for write processing to the cache memory management unit 230-2. (Step S50). The unconfirmed write confirmation request includes the corresponding secondary logical disk number.

  The cache memory management unit 230-2 searches all the entries of the cache block corresponding to the LDISK 80-2 indicated by the secondary logical disk number included in the unconfirmed write confirmation request (step S51). Next, the cache memory management unit 230-2 copies the undetermined bitmap included in the corresponding cache directory entry in the cache directory 232-2 corresponding to the corresponding cache block to the write-back map (step S52). ). That is, the cache memory management unit 230-2 copies (reflects) the state of the bit set to “1” in the undetermined bitmap, that is, the state of the bit indicating the range of the undetermined write data to the write back map. To do. Thereafter, the cache memory management unit 230-2 initializes the undetermined bitmap (step S53). That is, the cache memory management unit 230-2 resets the bits in the undetermined bitmap copied to the write-back map (here, all bits of the undetermined bitmap) to “0”.

  All caches corresponding to the cache memory management unit 230-2 and LDISK 80-2 execute the above-described copy process for the lock entry. Then, the cache memory management unit 230-2 notifies the primary data storage device 10-1 of status information indicating completion as a response to the unconfirmed write confirmation command from the primary data storage device 10-1 (step S54).

  At the time of completion by processing of such an unconfirmed write confirmation command, there is no unconfirmed write data in the cache memory 51-2.

  Next, in this embodiment, from the securing of the cache block or buffer in step S3 or S4 to the completion of the processing of the I / O request, the cache block and buffer used for entry of the corresponding write data are determined. Exclusively based on the status flag in the cache directory entry. That is, the cache block and the buffer in use are not used by other I / O requests. Hereinafter, the details of the process (step S3 or 4) at the time of securing the cache block executed by the cache memory management unit 230-i will be described with reference to the flowchart of FIG.

  First, when the cache memory management unit 230-i receives an I / O request (normal write request or unconfirmed write request) for write processing from the I / O management unit 220-i, Referring to the cache directory 232-i, the cache block entry corresponding to the write access range in the LDISK 80-i indicated by the access information included in the I / O request is searched (step S41). Then, the cache memory management unit 230-i determines whether an entry of the corresponding cache block is found as a result of the search for the cache block entry (step S42). That is, the cache memory management unit 230-i determines whether the corresponding cache block has already been secured.

  If an entry for the corresponding cache block is found (Yes in step S42), the cache memory management unit 230-i uses the cache block entry for processing for other I / O requests. (Step S44). The determination in step S44 is performed based on a status flag included in a cache directory entry (hereinafter referred to as a corresponding cache directory entry) in the cache directory 232-i corresponding to the corresponding cache block. If the corresponding cache block is not in use (No in step S44), the cache memory management unit 230-i determines whether the I / O request is a normal write request (step S45).

  The cache memory management unit 230-i is the cache memory management unit 230-2 included in the control device 20-2, and the I / O request is an unconfirmed write request sent from the primary data storage device 10-1. In this case, the determination in step S45 is No. In this case, the cache memory management unit 230-2 determines whether at least some bits of the write-back bitmap included in the corresponding cache directory entry are set (step S46). Based on this determination, it is determined whether the write-back data is included in the corresponding cache block.

  When the determination in step S46 is Yes, the cache memory management unit 230-2 includes the write-back data in the corresponding cache block that is not used in another I / O request in the corresponding cache directory entry. An I / O request for writing to the block area in the LDISK 80-2 designated by the logical disk number and logical address is sent to the RAID control unit 240-2 (step S47). The cache memory management unit 230-2 waits for notification of completion of writing from the RAID control unit 240-2 in response to this I / O request (step S48). At this stage, write data to be newly written to the corresponding cache block has not been received.

  As described above, when an unconfirmed write request is processed (No in step S45), as a result of the cache block search (step S41), there is an entry for the corresponding cache block (step S42 is Yes), and the corresponding cache directory entry. When at least a part of the bits of the write back bitmap is set (Yes in step S46), the cache memory management unit 230-2 writes the write back data in the corresponding cache block to the RAID control unit 240-. Requests 2 and waits for completion of writing. As a result, it is possible to prevent a situation in which the bits of the write-back bitmap and the indeterminate write bitmap included in the corresponding cache directory entry are set. In other words, if the data in the same cache block is write-back data and unconfirmed write data, it can be prevented from being indicated by the write-back bitmap and the unconfirmed write bitmap.

  Under such control of the cache memory management unit 230-2, the write-back data on the cache memory 51-2, that is, the cache memory determined by the processing of the unconfirmed write determination command from the primary data storage device 10-1. The data on 51-2 is always written to LDISK 80-2 without being overwritten with unconfirmed data.

  The cache memory management unit 230-i is waiting for the completion of writing, and when the completion of writing is notified from the RAID control unit 240-i (step S49), it is received from the current I / O management unit 220-i. The I / O management unit 220-i is requested to receive write data necessary for the write process specified by the I / O request (step S50). As a result, the cache memory management unit 230-i receives the write data, and ends the process when the cache block is secured.

  On the other hand, if the entry of the corresponding cache block is not found (No in step S42), the cache memory management unit 230-i newly secures a cache block (step S43), and then executes step S50. If the entry of the corresponding cache block is being used in processing for another I / O request (Yes in step S44), the cache memory management unit 230-i proceeds to step S48, and the I / O Wait for O request to complete. Subsequent operations are the same as when the process proceeds from step S47 to step S48.

  If all the bits of the write-back bitmap included in the corresponding cache directory entry have not been set (No in step S46), the cache memory management unit 230-i proceeds to step S50, and this I / The I / O management unit 220-i is requested to receive write data necessary for the write process specified by the I / O request received from the O management unit 220-i.

  On the other hand, the cache memory management unit 230-i is the cache memory management unit 230-1 included in the control device 20-1 (first control device), and the I / O management unit 220-1 received this time If the / O request is a normal write request sent from the host device 13-1 (Yes in step S45), the cache memory management unit 230-1 proceeds to step S50, and the write specified by this I / O request The I / O management unit 220-1 is requested to receive write data necessary for processing.

  If the bit range set in the write-back bitmap and the write access range indicated by the unconfirmed write request do not overlap even in the same cache block, the corresponding cache block is not necessarily obtained by executing step S47. There is no need to write the write-back data inside. Therefore, instead of step 46, a new step of determining whether the bit range set in the write-back bitmap and the write access range indicated by the unconfirmed write request may be applied. . Then, when the determination of this new step is Yes, the cache memory management unit 230-i requests the RAID control unit 240-i to write the write-back data of the overlapping portion included in the corresponding cache block ( Step S47) may wait for the completion of the writing (step S48). As a result, there is an area in the cache block in which both the bit of the write-back bitmap and the bit of the indeterminate write bitmap are set while preventing unnecessary writing of the cache block data. Can be prevented.

  Next, when the replication state is the SPLIT state, the operation of the primary data storage device 10-1 when a CDB including a normal write command is transmitted from the host device 13-1 to the primary data storage device 10-1 is simple. Explained. In this case, the primary data storage device 10-1 functions as a simple data storage device that is not a replication master. Therefore, in the primary data storage device 10-1, the normal write request processing (steps S1, S4, 6, S7, S8, S10 to S12, and S29) is executed in the flowcharts of FIGS. Is done.

  Next, the operation of the primary data storage device 10-1 when the replication state is the COPY state will be briefly described. In this case, the replication management unit 260-1 simply sends status information indicating write completion to the host device 13-1 instead of the processing (steps S13 to S20) of the replication management unit 260-i in the flowcharts of FIGS. A process of notifying (a process corresponding to step S20) is performed. Here, unlike the SYNC state, the processing of the buffering I / O list 264c-1 and the pending I / O list 264b-1 in the I / O management list 264-1 is not performed. Then, the replication management unit 260-1 makes a request to the communication port management unit 270-1 to send a confirmed write command corresponding to the normal write command to the secondary data storage device 10 under the control of the communication port management unit 270-1. Send to -2.

  Here, in the data storage system 100, it is assumed that the primary site 100-1 goes down due to a large-scale disaster or the like, and the primary data storage device 10-1 becomes inaccessible. In this case, the secondary data storage device 10-2 transitions to the SPLIT state according to an instruction from the host device 13-2. However, since the primary data storage device 10-1 is inaccessible, the secondary data storage device 10-2 transitions to the error SPLIT state instead of the normal SPLIT state. In the present embodiment, the secondary logical disk that is the target of the process of transitioning to the error SPLIT state is LDISK 80-2 that corresponds to LDISK 80-1.

  In the process of transitioning to the error SPLIT state, the cache memory management unit 230-2 discards the unconfirmed write data stored in the cache memory 51-2 at that time. As a result, the state of the secondary data storage device 10-2 can be rolled back to the time when the unconfirmed data is finally confirmed. That is, the LDISK 80-2 can be restored to the content at the time when the unconfirmed write confirmation command from the primary data storage device 10-1 was last processed.

  Undetermined write data is discarded as follows. First, the cache memory management unit 230-2 searches all the entries of the cache block corresponding to the LDISK 80-2 that are targets of the process of transitioning to the error SPLIT state. Next, the cache memory management unit 230-2 resets all the bits in the undetermined bitmap included in the corresponding cache directory entry in the cache directory 232-2 corresponding to the corresponding cache block. As a result, the undetermined write data stored in the cache memory 51-2 is discarded at the start of the process of transitioning to the error SPLIT state.

  When the difference between LDISK 80-1 and LDISK 80-2, that is, the difference between replication pairs is managed using a difference table or the like, a difference corresponding to an area in which undetermined write data is discarded may be set.

  In the above-described data storage system according to the present embodiment, the case where there is one replication pair has been described, but the data storage system may have a plurality of replication pairs. In such a data storage system, a configuration in which a plurality of replication pairs that require data consistency is grouped, and an indeterminate write process and an indeterminate write commit process are performed for each group (consistency group) It is also possible. In this case, the indoubt write confirmation command transmitted from the primary data storage device 10-1 to the secondary data storage device 10-2 may have a consistency group number instead of the secondary logical disk number.

  In this embodiment, in order to guarantee the order of write requests, data of the I / O management list 264-i in which these requests are connected in the order of requests is used.

  In this embodiment, asynchronous replication is applied. That is, in the present embodiment, the transfer of status information from the primary data storage device 10-1 to the host device 13-1 in response to the normal write request from the host device 13-1 to the primary data storage device 10-1 is the primary data storage device. It is not affected by the data transfer time from 10-1 to the secondary data storage device 10-2.

  Therefore, in the present embodiment, the write received by the primary data storage device 10-1 from the host device 13-1 before and after the unconfirmed data confirmation command is issued from the primary data storage device 10-1 to the secondary data storage device 10-2. Guarantees the order of the data. This is clear from the mechanism for preventing the write data in the cache memory 51-2 that has already been confirmed from being overwritten with unconfirmed data as described above. Further, the order when the same area of LDISK 80-1 is updated within the period from one unconfirmed data confirmation command to the next unconfirmed data confirmation command is as described above. The cache block is excluded until after the indefinite write to the secondary data storage device 10-2 is completed (data written later is overwritten with data written earlier). Absent).

  In the present embodiment, it is also possible to realize asynchrony in the case where write requests are continuously made in the same area during execution of the confirmation command. Note that when write requests are continuously made to the same area, the response to the host device can be reduced by transferring only the last requested write data when transferring write data to the secondary site. Is possible.

  In the present embodiment, the maximum rollback time can be guaranteed by the fixed cycle indicated by the fixed cycle information. This maximum rollback time indicates how much the content of LDISK 80-2 can be rewound to the content of LDISK 80-1 before that time when primary site 100-1 is down.

  Further, according to the present embodiment, a dedicated relay transfer device is not required between the primary site 100-1 and the secondary site 100-2, and the cache memory 51-1 is provided in the primary site 100-1 and the secondary site 100-2. In addition to 51-2, a relatively inexpensive asynchronous replication that does not require a dedicated buffer can be realized. Further, protocol overhead such as assigning sequence numbers can be reduced.

  The present embodiment is not limited as it is, and can be embodied by modifying the constituent elements without departing from the scope of the invention in the implementation stage. In addition, various inventions can be formed by appropriately combining a plurality of components disclosed in the embodiment. For example, some components may be deleted from all the components shown in the present embodiment. In the present embodiment, the data transfer buffer is secured in the cache memory 51-i. However, the data transfer buffer may be secured in a storage medium such as LDISK, HDD, or SSD. In this case, it is assumed that the management unit of the storage medium to which the buffer is secured has a status flag for indicating whether the buffer is secured, instead of the cache memory management unit.

100-1 ... primary site, 100-2 ... secondary site, 10-1 ... primary data storage device (first data storage device), 10-2 ... secondary data storage device (second data storage device), 13- DESCRIPTION OF SYMBOLS 1, 13-2 ... Host device, 20-i ... Control device, 80-i ... Logical disk (LDISK, storage medium), 11-1, 11-2 ... Data communication path, 21-i ... CPU, 31-i ... Program memory, 51-i ... Cache memory, 230-i ... Cache memory management unit, 231-i ... Cache directory storage unit, 232-i ... Cache directory, 260-i ... Replication management unit, 261-i ... Replication management Data storage unit, 262-i ... replication management table, 263-i ... I / O management list storage unit, 264-i, ... I / O management list, 264a-i ... execution I / O list, 264b-i ... pending I / O re Strike, 264c-i ... Buffering I / O list

Claims (5)

A first data storage device having a first storage medium for storing data and a first control device for controlling access to the first storage medium;
A second storage medium for storing data and a second control device for controlling access to the second storage medium, and connected to the first data storage device via a data communication path A second data storage device,
The first control device stores a first cache memory for storing data to be read from or written to the first storage medium, and write data to be transmitted to the second data storage device A buffer area for managing the first cache memory, a first cache memory managing means for managing access to the first cache memory, and the first and second storage media for the data stored in the first storage medium. Replication management means for performing replication management with a specific replication state for operating as a mirror in which a replica is stored in the second storage medium,
The second control device includes a second cache memory that stores data to be read from or written to the second storage medium,
In the specific replication state, the first cache memory management means, when data write to the first storage medium is designated from an external device, the first cache memory and the buffer area Write the specified data to each,
The replication management means requests the second data storage device for an unconfirmed write for writing the write data written in the buffer area as unconfirmed write data to the second cache memory;
When the write data exceeds a set amount by requesting the indeterminate write, or when a predetermined timing arrives, the undetermined write data is transferred from the buffer area to the second cache memory. A data storage system that requests unconfirmed write confirmation from the second data storage device to confirm data that has already been written as write-back data to be written to the second storage medium.   The replication management means, when performing a plurality of unconfirmed write requests to the same area of the second cache memory, among the plurality of unconfirmed write requests, The data storage system according to claim 1, wherein only data is transmitted.   3. The data storage system according to claim 1, wherein the replication management unit requests the unconfirmed write to the second data storage device when a predetermined replication cycle arrives. .   The replication management means requests the second data storage device for the unconfirmed write when the amount of data in the buffer area exceeds a predetermined amount of data. 2. The data storage system according to 2. A first data storage device having a first storage medium for storing data and a first control device for controlling access to the first storage medium; and a second data storage device for storing data A second data storage device having a storage medium and a second control device for controlling access to the second storage medium and connected to the first data storage device via a data communication path; The first control device includes a first cache memory for storing data read or written to the first storage medium, and a write to be transmitted to the second data storage device. A data storage system comprising a second cache memory for storing data to be read from or written to the second storage medium. A asynchronous replication method applied to,
In a specific replication state for operating the first and second storage media as a mirror when a copy of the data stored in the first storage medium is stored in the second storage medium, external When writing data to the first storage medium from the device is designated,
The first controller writing the designated data to the first cache memory as write-back data to be written to the first storage medium;
Writing the designated data into the buffer area as write data to be transmitted to the second data storage device;
When the predetermined replication cycle arrives, the first control device performs an unconfirmed write for transferring the write data written in the buffer area to the second cache memory. Requesting the storage device;
When it is determined that the write data transferred to the second cache memory exceeds the predetermined amount by requesting the indeterminate write, or when a predetermined fixed period has arrived The first controller determines the unconfirmed write determination for determining the write data transferred to the second cache memory as write-back data to be written to the second storage medium. And a step of requesting the data storage device.

Images