Apparatus for determining backup configuration of storage system

JP2025144860A5Pending Publication Date: 2026-03-03HITACHI VANTARA LTD
View PDF 0 Cites 0 Cited by

Patent Information

Authority / Receiving Office
JP · JP
Patent Type
Applications
Current Assignee / Owner
Filing Date
2024-03-21
Publication Date
2026-03-03

AI Technical Summary

Technical Problem

Conventional backup configurations for storage systems face performance issues due to CPU and memory allocation conflicts between data reading from storage drives and backup processes, leading to decreased bandwidth utilization.

Method used

A backup configuration apparatus utilizing SmartNICs to offload protocol processing from storage controllers, allowing separate front-end interfaces to handle backup and block processing independently, optimizing resource allocation based on network and system performance.

Benefits of technology

Enhances backup performance by reducing bottlenecks and ensuring efficient use of CPU and memory resources, minimizing impact on client IO operations.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 00000000_0000_ABST
    Figure 00000000_0000_ABST
Patent Text Reader

Abstract

To determine an appropriate backup configuration of a storage system.SOLUTION: An apparatus determines a backup configuration of a storage system. The storage system includes multiple front-end interfaces. The apparatus stores configuration determination information. The configuration determination information includes network performance information indicating performance of a network between the storage system and a backup destination, interface performance information indicating performance of the front-end interfaces, and performance requirement information indicating performance requirements for a host IO. Based on the configuration determination information, the apparatus determines a front-end interface that reads backup data from a storage device and a front-end interface that transmits the backup data to the backup destination.SELECTED DRAWING: Figure 18
Need to check novelty before this filing date? Find Prior Art

Description

[Technical Field]

[0001] The present invention relates to a backup configuration for a storage system. [Background technology]

[0002] The hybrid cloud storage market is expanding. One of the main use cases for hybrid cloud storage is backup to cloud storage. Because huge volumes of data need to be transferred from on-premise storage systems to cloud storage, backup software must have high transfer performance.

[0003] Background art for the present disclosure is U.S. Patent No. 8,156,293. U.S. Patent No. 8,156,293 discloses a storage system in which a plurality of first storage control modules process I / O operations related to data stored in disk devices communicating with each storage control module, a first type of storage control software to be installed in a first storage control module among the storage control modules from a plurality of types of storage control software that can be installed and executed by the first storage control modules, the designated first type of storage control software is installed in the first storage control module, and the first storage control module executes the first type of storage control software to process the first type of I / O operations. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] U.S. Patent No. 8,156,293 Summary of the Invention [Problem to be solved by the invention]

[0005] Conventional technology can be applied to the front-end interface to execute backup processing, which involves encoding data read from a storage drive (also called a disk or storage device) and then encrypting or compressing it before transferring it to a backup destination.

[0006] For example, if the bandwidth between the storage system and the backup destination increases, the backup performance will decrease relative to the bandwidth. This is because the CPU and memory of the same front-end interface are allocated to the process of reading data from the storage drive (also called a disk) and the backup process, so only a portion of the CPU and memory can be allocated to the backup process.

[0007] In this way, the appropriate backup configuration for a storage system can change depending on conditions such as the performance of the storage system and the network bandwidth. [Means for solving the problem]

[0008] One aspect of the present invention is an apparatus for determining a backup configuration for a storage system, comprising a processor and a memory device, wherein the storage system comprises a plurality of front-end interfaces, and the memory device stores configuration determination information, the configuration determination information comprising network performance information indicating the performance of a network between the storage system and a backup destination, interface performance information indicating the performance of the front-end interfaces, and performance requirement information indicating performance requirements for host IO, and the processor determines, based on the configuration determination information, a front-end interface for reading backup data and a front-end interface for sending the backup data to the backup destination. [Effects of the Invention]

[0009] According to one aspect of the present invention, an appropriate backup configuration for a storage system can be determined. [Brief explanation of the drawings]

[0010] [Figure 1] FIG. 2 is a configuration diagram illustrating a backup configuration according to the first embodiment. [Figure 2] FIG. 2 is a hardware configuration diagram of a storage system according to a first embodiment. [Figure 3] FIG. 2 is a hardware configuration diagram of an FE I / F according to the first embodiment. [Figure 4A] 10 shows an example of the configuration of backup configuration information. [Figure 4B] 10 shows an example of the configuration of backup configuration information. [Figure 5] The flowchart shows the backup process using two FE I / Fs. [Figure 6] 10 shows a flowchart of the failure response process using the FE I / F. [Figure 7] FIG. 10 is a configuration diagram illustrating a backup configuration in a second embodiment. [Figure 8] FIG. 10 is a hardware configuration diagram of a storage system according to a second embodiment. [Figure 9] 10 shows a flowchart of a backup process in the second embodiment. [Figure 10] FIG. 10 is a configuration diagram illustrating a backup configuration in a third embodiment. [Figure 11] FIG. 2 is a diagram illustrating an example of a configuration of a management device. [Figure 12] 11 shows a flowchart of a backup process according to a third embodiment. [Figure 13] 11 shows a flowchart of a failure handling process according to a third embodiment. [Figure 14] FIG. 10 is a configuration diagram illustrating a backup configuration in a fourth embodiment. [Figure 15] 13 shows a flowchart of a backup process according to a fourth embodiment. [Figure 16] 10 shows an example of the configuration of configuration determination information. [Figure 17] 10 shows an example of the configuration of backup configuration management information. [Figure 18]13 shows a flowchart of a backup configuration determination process according to a fifth embodiment. [Figure 19] 19 shows a flowchart of a backup configuration determination process according to a sixth embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0011] Several embodiments will be described below with reference to the drawings. These embodiments do not limit the scope of the present invention, and not all of the elements described in the embodiments are necessarily required to solve the problems of the present invention. Hereinafter, for convenience, the description will be divided into multiple sections or embodiments, where necessary. However, unless otherwise specified, these sections or embodiments are not unrelated to each other, and one is related to the other as a partial or complete modification, detail, supplementary explanation, etc. Furthermore, when the number of elements (including the number, numerical value, amount, range, etc.) is mentioned below, it is not limited to the specific number, and may be more or less than the specific number, unless otherwise specified or when it is clearly limited to a specific number in principle.

[0012] In one embodiment of this specification, a SmartNIC (Network Interface Card) is installed in a storage system, and a SmartNIC-utilizing storage is assumed in which protocol processing is offloaded from the processor of a controller (also called a storage controller) that controls data access in the storage system to the SmartNIC.

[0013] SmartNIC is a highly functional network card and front-end interface device that can be programmed (added) with desired functions by software or hardware. In addition to the communication processing of the physical layer and data link layer that conventional network cards perform, SmartNIC can also perform functions of the network layer, transport layer, and application layer above the transport layer.

[0014] The following description of SmartNIC can be applied to interface devices whose functions can be programmed by software executed by a processor, as well as to interface devices with programmable logic circuit configurations such as FPGAs (Field Programmable Gate Arrays). FPGAs may include logic circuits that realize each function implemented by a program and cache memory used in operations.

[0015] In one embodiment of this specification, a backup configuration for a storage system is determined based on preset conditions. This allows an appropriate backup configuration to be determined based on the status of the storage system, including the connected network. Below, several backup configurations for storage systems are described, followed by a method for determining the backup configuration for a storage system. [Example]

[0016] FIG. 1 is a configuration diagram that schematically illustrates a backup configuration in Example 1. A client 40 performs IO access to a storage system 1 via a host network 30. The IO access includes reading data from and writing data to a storage device unit 20. The storage device unit 20 includes multiple storage devices (also called storage drives). The host network 30 is, for example, a LAN (Local Area Network).

[0017] The storage system 1 includes one or more controllers and multiple front-end interfaces (FE I / Fs). In the configuration example shown in FIG. 1, the storage system 1 includes two controllers 100A and 100B, three FE I / Fs 110A1, 110A2, and 110A3 of the controller 100A, and three FE I / Fs 110B1, 110B2, and 110B3 of the controller 100B. In FIG. 1, for ease of explanation, the FE I / Fs are arranged outside the controllers, but the FE I / Fs may be included in the controllers. Any controller shown in FIG. 1 is represented as controller 100, and any FE I / F is represented as FE I / F 110.

[0018] The FE I / F 110 executes block processing. Block processing is a block protocol process, for example, an iSCSI Target. The block processing passes a read or write request received from a request source (for example, a client 40) to the controller 100 in accordance with the request. The controller 100 transfers data from the storage device unit 20 to the request source, or writes data received from the request source to the storage device unit 20.

[0019] A SmartNIC is used for the FE I / F 110, and the FE I / F 110 can execute protocol processing. In this embodiment, the storage system 1 is a block storage, and iSCSI is assumed as the communication protocol between the client 40 and the storage system 1. Note that the storage system 1 does not have to be a block storage, and other communication protocols, such as FC-SCSI (FibreChannel Small Computer System Interface), NVMe / TCP, NVMe / RDMA (Remote Direct Memory Access), and FC NVMe, can also be used.

[0020] The storage system 1 executes a backup process (backup process sequence) of data stored in the storage device unit 20 to cloud storage. The storage system 1 transmits the backup data to cloud storage in the cloud 2 via a wide area network (WAN) 3. The backup process may be executed, for example, on a volume-by-volume basis. The backup destination may also be on-premise storage connected via a network.

[0021] In this embodiment, two FE I / Fs 110 that form a pair execute backup processing from the storage system 1 to the cloud storage. One FE I / F 110 each of different controllers 100A and 100B forms a pair. The two FE I / Fs 110 are inserted, removed, and managed as a pair.

[0022] Redundancy can be improved by pairing FE I / Fs 110 included in different controllers 100. For example, in the example shown in Fig. 1, FE I / F 110A3 and FE I / F 110B3 execute backup processing. Note that two FE I / Fs 110 of the same controller 100 may execute backup processing.

[0023] 1, the FE I / F 110A3 uses the FE I / F 110B3 to control the execution of backup processing. Specifically, the FE I / F 110A3 requests the FE I / F 110B3 to perform block processing for backup. The block processing for backup includes reading backup data from the storage device unit 20.

[0024] The FE I / F 110A3 acquires the backup data read from the storage device unit 20 via the FE I / F 110B3, performs a predetermined encoding process (including encryption and compression, for example) on the data, and transfers it to the backup destination.

[0025] The FE I / F 110A3 requests the FE I / F 110B3 to transfer the backup data specifying the address of the backup data via the backup network 60. The backup network 60 is, for example, a LAN. The backup network 60 may be common to the host network 30.

[0026] The FE I / F 110B3 reads the specified backup data from the storage device unit 20 via the controller 100B, and transfers the backup data to the FE I / F 110A3 via the backup network 60. This is similar to the block processing in response to an IO request from the host.

[0027] The FE I / F 110A3 performs a predetermined encoding process (processing) on ​​the acquired backup data. The encoding process may include encryption, compression, conversion to a format suitable for backup, etc. The FE I / F 110A3 transmits the processed backup data to cloud storage in the backup destination cloud 2 via the backup network 60 and WAN 3. In this way, by having different FE I / Fs 110 perform the backup process and the block processing for backup, the possibility that the FE I / F 110 will become a bottleneck and lengthen the backup processing time can be reduced.

[0028] Here, the FE I / Fs 110A3 and 110B3 are excluded from being responsible for block processing for IO from the client 40. In this example, the FE I / Fs 110A3 and 110B3 are connected to the backup network 60 and are not connected to the host network 30. This makes it possible to avoid the backup from affecting IO from the client 40. Note that the FE I / Fs 110A3 and 110B3 may also be connected to the host network 30 and perform host processing outside of the backup processing period.

[0029] The other FE I / Fs 110A1, 110A2, 110B1, and 110B2 execute block processing for the client 40 and are excluded from the backup processing sequence. In this example, the FE I / Fs 110A1, 110A2, 110B1, and 110B2 are connected to the host network 30 and are not connected to the backup network 60. The FE I / Fs 110A1, 110A2, 110B1, and 110B2 may be connected to the backup network 60.

[0030] All processor cores of the FE I / F 110A3 are not exclusively assigned to processes (applications) other than the backup process, and all processor cores are capable of executing the backup process. Furthermore, all processor cores of the FE I / F 110B3 are not exclusively assigned to processes (applications) other than the block process, and all processor cores are capable of executing the block process. As described above, the FE I / Fs 110A3 and 110B3 do not accept I / O from the client 40 during the backup process sequence.

[0031] 2 is a hardware configuration diagram of a storage system 1 of Example 1. The storage system 1 is connected to a client 40 via a host network 30. The storage system 1 is connected to a management device 50 via a backup network 60. The backup network 60 is connected to a cloud 2 via an external WAN 3.

[0032] The storage system 1 includes a storage control device 10 and a storage device unit 20. The storage control device 10 includes multiple controllers, two of which, 100A and 100B, are shown in Figure 2. To improve the availability of the storage system 1, a dedicated power supply may be provided for each controller 100, and power may be supplied to each controller 100 using that dedicated power supply. There may also be multiple storage control devices 10, and the controllers 100 may be connected to each other via an HCA (Host Channel Adaptor) network.

[0033] The controllers 100A and 100B have the same configuration. The controller 100 includes a plurality of FE I / Fs 110, a back-end interface (BE I / F) 120, a CPU 130 which is a processor, a memory 140 which is a main memory, and a cache 150. These are connected to each other by a communication path such as a bus.

[0034] The FE I / F 110 is a programmable network interface that uses a SmartNIC or the like. Block protocol processing and backup processing run on the FE I / F 110. Details of the FE I / F 110 will be described later using FIG. 3. The BE I / F 120 is an interface device that allows the controller 100 to communicate with the storage device unit 20.

[0035] The CPU 130 controls the operation of the block storage. The memory 140 is, for example, a RAM (Random Access Memory), and temporarily stores programs and data for the operation control of the CPU 130. The memory 140 stores a block storage control program P1. The cache 150 temporarily stores write data from the client 40 or the FE I / F 110 and data read from the storage device unit 20. Note that the data stored in the memory 140 may also be stored in the storage device unit 20.

[0036] The block storage control program P1 provides the FE I / F 110 with logical devices (LDEVs), which are logical storage areas based on the storage device units 20. The FE I / F 110 can access any LDEV. This allows the FE I / F 110 to use the LDEV as a storage destination for the client 40's data.

[0037] The storage device unit 20 has a plurality of PDEVs 21. The PDEVs 21 may be HDDs (Hard Disk Drives) or other types of storage devices (non-volatile storage devices), for example, FM (Flash Memory) devices such as SSDs (Solid State Drives). The storage device unit 20 may have different types of PDEVs 21. Furthermore, a RAID group may be configured with a plurality of PDEVs 21 of the same type. Data is stored in the RAID group according to a predetermined RAID level.

[0038] The client 40 is a device that accesses the storage system 1, and sends data input / output requests (data write requests, data read requests) to the storage system 1. The client 40 sends data input / output requests to the storage system 1 in block units.

[0039] The management device 50 has a user interface such as a GUI (Graphical User Interface) or a CLI (Command Line Interface), and provides functions for a user or operator to control and monitor the storage system 1.

[0040] 3 is a hardware configuration diagram of the FE I / F 110 of the first embodiment. The FE I / F 110 has a network I / F 111, an internal I / F 112, a CPU 113, a memory 114, and a storage device 116. These are connected to each other by a communication path such as a bus. The memory 114, the storage device 116, and a combination thereof constitute a memory device.

[0041] The network I / F 111 is an interface device for communicating with the client 40. An IP address is set in the network I / F 111 and the network I / F 111 is used as a network port for communication. The IP address is an identifier on the network, and the client 40 communicates with the FE I / F 110 through the IP address set in the port.

[0042] The internal I / F 112 is an interface device that communicates with the controller 100. The internal I / F 112 is connected to the CPU of the controller 100 via, for example, PCIe (Peripheral Component Interconnect-Express).

[0043] The CPU 113 is a processor that controls the operation of the FE I / F 110. The memory 114 is a main memory that temporarily stores programs and data used to control the operation of the CPU 113. The memory 114 stores a backup program P11, a block protocol server program P15, a failure response program P17, and backup configuration information T1. The programs and information stored in the memory 114 may also be stored in the storage device 116. The backup program P11, the failure response program P17, and the backup configuration information T1 only need to be stored in the FE I / F 110, which may control the execution of backup processing.

[0044] The backup program P11 executes and controls the backup process. Details of the backup process will be described later. The block protocol server program P15 receives various requests, such as read / write, from the request source and processes the block protocol included in these requests. The block protocol server program P15 processes the received requests and converts them into block access command requests to the controller 100. The block protocol server program P15 communicates with the CPU 130 of the controller 100 and processes data reads and writes to the LDEVs.

[0045] The cache 115 is a device (storage area) that temporarily stores user data, backup data, etc. that are sent to and received from the client 40. The storage device 116 is a non-volatile storage device that stores programs, tables, etc. of the FE I / F 110, and for example, a flash memory can be used.

[0046] 4A and 4B show examples of backup configuration information T1. The backup configuration information T1 manages information for backup processing. FIG. 4A shows an example of backup configuration information T1 stored in the FE I / F 110 that controls the execution of backup processing, and FIG. 4B shows an example of backup configuration information T1 stored in the FE I / F 110 that executes block processing for backup.

[0047] The backup configuration information T1 includes a status column C11, a CPU allocation to backup program column C12, a memory allocation to backup program column C13, and a block data read destination column C14 for backup processing.

[0048] The status column C11 indicates either a normal status or a paired FE IF failure status. The normal status is a status in which the FE IF pair is operating without a failure. The paired FE IF failure status is a status in which a failure has occurred in the other FE IF of the pair. Each entry indicates information on a normal status in which the FE IF is operating normally or information on a status in which a failure has occurred in the other FE IF of the pair.

[0049] The CPU allocation to backup program column C12 indicates the number of CPU cores allocated to the backup program P11. The memory allocation to backup program P11 column C13 indicates the proportion of memory allocated to the backup program P11. The block data read destination column C14 for backup processing indicates the FE IF 110 that reads data from the storage device unit 20.

[0050] 4A shows the contents of backup configuration information T1 held by the FE IF 110A3 (see FIG. 1), which controls the execution of backup processing. In normal conditions, the block data is read from the other FE IF 110B3 (see FIG. 1), which is the other of the pair. In the FE IF 110A3, the number of CPU cores allocated to the backup program P11 is 8, and the memory allocation ratio is 100%. In other words, all CPU cores are allocated.

[0051] If a failure occurs in the FE IF 110B3, the FE IF 110A3 (its own FE IF) controls the execution of the backup process and reads the backup data from the storage device unit 20. In other words, the FE IF 110A3 executes block processing and the encoding and transfer processing of the backup data read thereby. At this time, the number of CPU cores allocated to the backup program P11 in the FE IF 110A3 is 4, and the memory allocation ratio is 50%.

[0052] 4B shows the contents of backup configuration information T1 held by the FE IF 110B3 that executes block processing for backup. In normal conditions, the block data read destination is the FE IF 110B3 (its own FE IF). The number of CPU cores allocated to the backup program P11 in the FE IF 110B3 is 0, and the memory allocation ratio is 0%. In other words, the backup program P11 is not running.

[0053] If a failure occurs in the FE IF 110A3, the FE IF 110B3 (its own FE IF) controls the execution of the backup process and reads the backup data from the storage device unit 20. In other words, the FE IF 110B3 executes block processing and the encoding and transfer processing of the backup data read thereby. At this time, the number of CPU cores allocated to the backup program P11 in the FE IF 110B3 is 4, and the memory allocation ratio is 50%.

[0054] As described above, the backup configuration information T1 manages the hardware resources to be allocated to backup processing and the FE IF from which block data is read for backup processing in both normal and failed states.

[0055] Next, an example of backup processing using two FE I / Fs 110 will be described. Fig. 5 shows a flowchart of backup processing using two FE I / Fs 110. In the following, it is assumed that the FE I / Fs 110A3 and 110B3 shown in Fig. 1 execute the backup processing.

[0056] First, the backup program P11 of the FE I / F 110A3 identifies the data to be backed up (S101). Specifically, it identifies the storage address of the data to be backed up. Information on the data to be backed up can be sent from the client 40 or the management device 50, for example.

[0057] Next, the backup program P11 requests the block processing on the paired FE I / F 110B3 to read the data to be backed up (S102). Specifically, the backup program P11 sends a read request specifying the address of the data to be backed up to the FE I / F 110B3.

[0058] The block protocol server program P15 of FE I / F 110B3 receives the read request from FE I / F 110A3, reads the data at the address indicated by the read request from storage device unit 20, and returns it to FE I / F 110A3 (S103). Specifically, the block protocol server program P15 converts the read request into an internal read command and sends it to CPU 130 of controller 100B. CPU 130 reads the data at the specified address from storage device unit 20.

[0059] The FE I / F 110A3 stores the backup target data received from the FE I / F 110B3, for example, in the cache 115. The backup program P11 of the FE I / F 110A3 compresses the backup target data (S104). Note that a different encoding process may be executed instead of or in addition to compression. The backup program P11 transmits the compressed backup target data to the cloud 2 via the networks 60 and 3 and stores it (S105).

[0060] Next, the processing of the FE I / F 110 in the event of a failure will be described. Figure 6 shows a flowchart of the failure response processing by the FE I / F 110. Suppose a failure occurs in either the FE I / F 110A3 or 110B3. The failure response program P17 of each of the FE I / Fs 110A3 and 110B3 can monitor the status of the other FE I / F 110 and detect the failure that has occurred. For example, a heartbeat signal can be used.

[0061] First, the failure response program P17 detects a failure in the paired FE I / F 110 (S201). The failure response program P17 references the backup configuration information T1 and changes the resource allocation of the backup program P11 and the block protocol server program P15 (S202).

[0062] If a failure occurs in one of the pair, the other FE I / F 110 continues the backup process. Therefore, if a failure occurs in one of the pair's FE I / F 110, the program configuration running in the other FE I / F 110 is changed to the basic method, that is, a configuration in which the backup program P11 and block protocol server program P15 run.

[0063] Specifically, in the FE I / F 110A3, under normal conditions, 8 cores and 100% of the memory are allocated to the backup program P11, and 0 cores are allocated to the block protocol server program P15, i.e., it is not running. In the event of a failure, 4 cores and 50% of the memory are allocated to the backup program P11 and the block protocol server program P15, respectively.

[0064] On the other hand, in the FE I / F 110B3, under normal conditions, 8 cores and 100% of the memory are allocated to the block protocol server program P15, and 0 cores are allocated to the backup program P11, i.e., it is not running. In the event of a failure, 4 cores and 50% of the memory are allocated to the backup program P11 and the block protocol server program P15, respectively. [Example]

[0065] Other embodiments of the present specification will be described below. Differences from the first embodiment will be mainly described below. Unless otherwise specified, the description of the first embodiment can be applied to this embodiment. In this embodiment, the FE IF 110 that controls the execution of the backup process requests a block process from an FE IF 110 other than the FE IF 110 that forms the pair (all resource allocation outside pair read configuration).

[0066] The different FE IF 110 also processes requests from the client 40. If the bandwidth of the backup network 60 is insufficient or the performance of the paired FE IF 110 is insufficient, backup processing can be performed quickly by using another network or FE IF 110.

[0067] Fig. 7 is a configuration diagram illustrating a backup configuration in Example 2. Compared to the backup configuration shown in Fig. 1, the FE IF1110A3 requests block processing (reading) of backup data from the other FE IFs 110A1, 110A2, 110B1, and 110B2 instead of the FE IF 1110B3 that configures the pair. In the configuration example shown in Fig. 2, the backup data is transferred to the FE IF 1110A3 via the host network 30.

[0068] By requesting block processing from multiple FE IFs 110, the processing load can be distributed. The destination of the block processing request for backup also executes the block processing requested by the client 40, thereby reducing the impact on that processing. Note that the FE IF 1110A3 executes the backup program P11 and does not execute the block protocol server program P15. The host network 30 can enable faster transfers when the bandwidth of the backup network 60 is insufficient. Note that other dedicated networks or internal communications (such as DMA) may be used instead of or in addition to the host network 30.

[0069] 7, the data to be backed up is read via another FE IF 110 in the same controller 100A as the FE IF 110A3 and an FE IF 110 in another controller 100B. The FE IF 110 that executes block processing of the data to be backed up may be only the FE IF 110 in the same controller 100A as the FE IF 110A3 that transfers the data to the backup destination, or only the FE IF 110 in a different controller 100B.

[0070] Fig. 8 is a hardware configuration diagram of a storage system 1 of Example 2. Compared to the configuration example shown in Fig. 2, the FE IF110 that controls the execution of backup processing and the FE IF110 that forms a pair with it are connected to the host network 30 in addition to the backup network 60. Note that if the transfer of backup data is executed via a communication path different from the host network 30, such as an internal communication path, the above two FE IFs 110 do not need to be connected to the host network 30.

[0071] Fig. 9 shows a flowchart of the backup process in the embodiment 2. The steps other than step S303 are the same as those in the backup process shown in Fig. 5. In step S303, the backup program P11 requests the block process on the FE IF 110 other than the pair to read the data to be backed up.

[0072] Candidates for the request destination FE IF 110 are specified in advance by the FE IF 110A3. The FE IF 110A3 selects a request destination from the candidate request destinations. Selection methods include a round-robin selection method for each I / O, or a method of checking the load of the candidate FE IF 110 for the request destination and selecting the FE IF 110 with the lowest load. Load information for the FE IF 110 can be acquired from the FE IF 110 in question. [Example]

[0073] Other embodiments of this specification will be described below. Differences from the first embodiment will be mainly described below. Unless otherwise specified, the description of the first embodiment can be applied to this embodiment. In this embodiment, the backup process, that is, the reading of data from the storage device unit 20 and the transfer of data to the backup destination, is distributed to a pair of FE IFs 110. If the performance of the FE IFs 110 is high compared to the network performance, the backup process can be performed quickly.

[0074] Fig. 10 is a configuration diagram illustrating a backup configuration in Example 3. Compared to the backup configuration shown in Fig. 1, two FE IFs 110A3 and 110B3 each control the execution of backup processing and perform block processing of backup data. In other words, each of the FE IFs 110A3 and 110B3 executes a backup program P11 and a block protocol server program P15.

[0075] 10, the management device 50 issues a backup instruction specifying an address to each of the pair of FE IFs 110A3 and 110B3. The management device 50 is connected to the backup network 60. This instruction may be sent from the controller 100 or the client 40.

[0076] 11 is an example of a configuration diagram of a management device 50. The management device 50 has a network I / F 51, a CPU 52 which is a processor, a memory 53, and a storage device 54. The memory 53, the storage device 54, and a combination thereof constitute a memory device. These are connected to each other by a communication path such as a PCI Express (Peripheral Component Interconnect Express) bus.

[0077] The network I / F 51 is an interface device for communicating with the storage system 1 and the client 40. The CPU 52 controls the operation of the management device 50. The memory 53 temporarily stores programs and data used to control the operation of the CPU 52. The memory 53 stores a distributed backup instruction program P51 and a failure response program P57. The programs and information stored in the memory 53 may be stored in a storage device 54. The storage device 54 stores programs and tables for the management device 50.

[0078] The distributed backup instruction program P51 instructs the multiple FE IFs 110 that execute backup processing to perform backup processing specifying the data to be backed up. The failure response program P57 monitors the status of the multiple FE IFs 110 that execute backup processing, and executes response processing if a failure occurs in any of the FE IFs 110.

[0079] 12 shows a flowchart of backup processing related to Example 3. The distributed backup instruction program P51 calculates the backup target range of each backup program P11 (S501). Next, the distributed backup instruction program P51 instructs each backup program to perform backup processing (S502). The instruction specifies the data to be backed up.

[0080] The backup program P11, which has received an instruction from the distributed backup instruction program P51, requests the block protocol server program P15 on the same FE IF 110 to read the data to be backed up (S503). The block protocol server program P15 reads the specified data to be backed up from the storage device unit 20 and returns it to the backup program P11 (S504). The subsequent steps S104 and S105 are as described with reference to Figure 5.

[0081] Next, a process to be performed when a failure occurs in the FE IF 110 that executes the backup process will be described. Fig. 13 shows a flowchart of the failure response process according to the third embodiment. The failure response program P57 monitors the status of the FE IF 110 that executes the backup process. The status monitoring may use heartbeat communication, for example.

[0082] The failure response program P57 detects a failure that has occurred in the FE IF 110 that executes backup processing (S601). The failure response program P57 identifies unprocessed backup target data that is the backup target data of the FE IF 110 in which the failure has occurred. The progress status of the backup processing may be reported from the FE IF 110 to the management device 50 at any time. The failure response program P57 notifies one or more FE IFs 110 that perform backup processing without a failure of a change to the backup processing target range so that the unprocessed backup target data is included (S602). Upon receiving the notification, the backup program P11 of the FE IF 110 executes backup processing of the changed backup processing target range (S603). [Example]

[0083] Other embodiments of this specification will be described below. Differences from the other embodiments will be mainly described below. Unless otherwise specified, the descriptions of the other embodiments can be applied to this embodiment. In this embodiment, each of the multiple FE IFs 110 executes the backup program P11 without performing block processing, and requests block processing of the data to be backed up from other FE IFs 110 that execute host processing. By having the multiple FE IFs 110 execute execution control of the backup processing, the load on them can be reduced.

[0084] FIG. 14 is a configuration diagram illustrating a backup configuration in the fourth embodiment. Compared to the configuration example shown in FIG. 7, in addition to the FE IF 110A3, an FE IF 110B3 controls the execution of backup processing. These form a pair. The FE IFs 110A3 and 110B3 execute the backup program P11, but do not execute the block protocol server program P15. The FE IFs 110A3 and 110B3 request block processing of backup data from different FE IFs 110.

[0085] 14, the FE IFs 110A3 and 110B3 request block processing of backup data from multiple other FE IFs 110 in the same controller 100. The FE IF 110A3 may request block processing of backup data from the FE IF 110 in a different controller 100B. Similarly, the FE IF 110B3 may request block processing of backup data from the FE IF 110 in a different controller 100A.

[0086] 10, the management device 50 issues a backup instruction specifying an address to each of the pair of FE IFs 110A3 and 110B3. The management device 50 is connected to the backup network 60. This instruction may be sent from the controller 100 or the client 40.

[0087] Next, a backup process related to the fourth embodiment will be explained. Fig. 15 shows a flowchart of the backup process related to the fourth embodiment. The distributed backup instruction program P51 calculates the backup target range of each backup program P11 (S501). Next, the distributed backup instruction program P51 instructs each backup program to perform backup processing (S502). The instruction specifies the data to be backed up.

[0088] The backup program P11, which has received an instruction from the distributed backup instruction program P51, requests the block protocol server program P15 on another FE IF 110 of the same controller 100 to read the data to be backed up (S703). The block protocol server program P15 reads the specified data to be backed up from the storage device unit 20, and returns it to the backup program P11 via the requesting FE IF 110 (S704). The subsequent steps S104 and S105 are as described with reference to FIG. 5.

[0089] Candidates for the request destination FE IF 110 are specified in advance in the FE IFs 110A3 and 110B3. The FE IF 110A3 selects a request destination from the candidate request destinations. Selection methods include a round-robin selection method for each I / O, or a method of checking the load on the candidate FE IFs 110 and selecting the FE IF 110 with the lowest load. Load information on the FE IF 110 can be acquired from the FE IF 110 in question. [Example]

[0090] Another embodiment of this specification will be described below. This embodiment describes a method for selecting a backup configuration to be applied to the storage system 1 from among multiple backup configuration candidates. Specifically, an appropriate backup configuration is selected from the all resource allocation pair read configuration (configuration 1) described in embodiment 1, the all resource allocation outside pair read configuration (configuration 2) described in embodiment 2, and the basic configuration. The basic configuration is a configuration in which only one FE IF 110 executes the backup program P11 and the block protocol server program P15.

[0091] Which backup configuration is most suitable depends on the customer's line bandwidth and requirements. For example, the all resource allocation pair read configuration (configuration 1), which is the backup configuration in the normal state described in the first embodiment, is expected to improve backup processing performance by more than twice as much as the basic configuration. On the other hand, unlike the basic configuration, the all resource allocation pair read configuration (configuration 1) requests block I / O for backup from the paired FE IF 110, consuming the bandwidth of the backup NW 60. As a result, the basic configuration may be more suitable depending on the bandwidth of the backup NW 60. Furthermore, since the configuration in the event of a failure is the same as the basic configuration, backup performance is lower than that of the all resource allocation pair read configuration (configuration 1) in the normal state.

[0092] The all resource allocation pair outside read configuration (configuration 2), which is the backup configuration in the normal state described in the first embodiment, also consumes the bandwidth of the host NW 30. Therefore, depending on the bandwidth of the host NW 30 and the host performance requirements, the basic configuration or the all resource allocation pair read configuration (configuration 1) may be more suitable.

[0093] In this embodiment, the backup configuration to be constructed is determined according to the customer's line bandwidth (WAN bandwidth or LAN bandwidth) and requirements (backup requirements or host performance requirements), and is set in the storage system 1. Predetermined management information is referenced to determine and set the backup configuration. This embodiment references configuration determination information and backup configuration management information. Setting of the backup configuration may be performed by, for example, the management device 50, the controller 100, or an administrator. The reference information may be implemented in these devices or other devices.

[0094] Fig. 16 shows an example of the configuration of configuration determination information T2. ​​The configuration determination information T2 includes information on the conditions for determining the backup configuration. The configuration determination information T2 includes a classification column C21, an item column C22, a value column C23, and a fixed / variable column C24. The classification column C21 indicates the classification of items referenced in determining the backup configuration. In the example configuration shown in Fig. 16, the network bandwidth, FE IF performance, and performance requirements are registered.

[0095] The item column C22 indicates items that are referenced when determining the backup configuration. In the configuration example shown in FIG. 16, items classified as network bandwidth include host network bandwidth, backup network bandwidth, and WAN bandwidth. Items classified as FE IF performance include backup performance and block performance of the basic configuration. Items classified as performance requirements include block performance requirements and backup performance requirements.

[0096] The value column C23 indicates the value of each item indicated by the item column C22. The fixed / variable column C24 indicates whether the value indicated by the value column C23 is a fixed value or a variable value. Fixed values ​​are never updated in the configuration determination information T2. ​​On the other hand, variable values ​​are updated as appropriate, for example, periodically.

[0097] Entry R21 indicates information about the host network bandwidth. Its value is 100 Gbps and can be a fixed value or a variable value. If it is a fixed value, the value initially registered is maintained, and if it is a variable value, it is updated as needed. Entry R22 indicates information about the backup network bandwidth. Its value is 100 Gbps and can be a fixed value or a variable value. If it is a fixed value, the value initially registered is maintained, and if it is a variable value, it is updated as needed. Entry R23 indicates information about the WAN bandwidth. Its value is 20 Gbps and can be a fixed value.

[0098] Entry R24 indicates information about the backup performance of the basic configuration. The value is a fixed value of 1.0 GB / s. As described above, the backup performance of the basic configuration is the data transfer performance when only one FE IF 110 reads backup data from the storage device unit 20 and transfers it to the cloud 2.

[0099] Entry R25 indicates information about the block performance per FE IF. Specifically, the block performance indicates the data read performance when the FE IF 110 is executing the block protocol server program P15 without executing the backup program P11. The value is 3 GB / s per FE IF.

[0100] Entry R26 indicates information about block performance requirements. The block performance requirements indicate the response performance requirements from the storage system 1 in response to an IO request from the client 40. The block performance requirement is a requirement required for the total block performance of all FE IFs 110 that respond to requests from the client 40. The value is 10 GB / s.

[0101] Entry R27 shows backup performance requirement information. The backup performance requirement is the performance requirement required for the backup process of storage system 1. The backup performance requirement is the requirement for the transfer performance of backup data from storage system 1 to cloud 2. The value is 1.5 GB / s.

[0102] Fig. 17 shows an example of the configuration of backup configuration management information T3. The backup configuration management information T3 includes information on the backup configurations of the selection candidates. In the example configuration shown in Fig. 17, the backup configuration management information T3 includes a backup configuration column C31, a backup processing FE IF column C32, a status column C33, a CPU allocation to backup program column C34, a memory allocation to backup program column C35, and a block data read destination column C36 for backup processing.

[0103] The backup configuration column C31 shows the name of the backup configuration to be selected. Here, two backup configurations, backup configuration 1 (first backup configuration) and backup configuration 2 (second backup configuration), and the basic configuration explained in Examples 1 and 2 are shown. Backup configuration 1 is a configuration in which all resource allocation configuration pairs are read, and backup configuration 2 is a configuration in which all resource allocation configuration pairs are read outside.

[0104] The backup processing FE IF column C32 indicates the FE IF 110 that executes the backup program P11 in each backup configuration. The status column C33 indicates the normal status or failure status of the FE IF pair. The failure status is a state in which a failure has occurred in only one of the FE IFs 110. The CPU allocation to backup program column C34 and the memory allocation to backup program column C35 indicate the CPU core and memory allocated to the backup program P11, respectively. The block data read destination column C36 for backup processing indicates the FE IF that reads data from the storage device unit 20 during backup processing.

[0105] Next, a backup configuration determination process according to this embodiment will be described. Fig. 18 shows a flowchart of the backup configuration determination process according to this embodiment. In the following, an example will be described in which the management device 50 executes this process, but the entity that executes this process is not particularly limited.

[0106] The management device 50 refers to the configuration determination information T2 (S801) and compares the backup performance of the basic configuration with the WAN bandwidth (S802). It is determined whether the WAN bandwidth will be a bottleneck in the basic configuration. If the backup performance of the basic configuration is equal to or greater than the WAN bandwidth (S802: NO), the management device 50 selects the basic configuration as the backup configuration to be set in the storage system 1 (S805).

[0107] If the backup performance of the basic configuration is smaller than the WAN bandwidth (S802: YES), the management device 50 compares the value obtained by multiplying the backup performance requirement by two with the backup network bandwidth (S803). It is determined whether the backup network 60 has insufficient bandwidth in backup configuration 1. If the value obtained by multiplying the backup performance requirement by two is smaller than the backup network bandwidth (S803: YES), the management device 50 selects backup configuration 1 as the backup configuration to be set in the storage system 1 (S807).

[0108] If the value obtained by multiplying the backup performance requirement by two is equal to or greater than the backup network bandwidth (S803: NO), the management device 50 compares the block performance of the host-allocated FE IF 110 that processes the request from the client 40 with the sum of the block performance requirement and the block performance in backup processing in the basic configuration (S804). It is determined whether using the host network 30 in backup processing will result in lower performance than in the basic configuration.

[0109] The block performance of the host-allocated FE IF 110 is the sum of the block performance of all the host-allocated FE IFs 110. Using the information shown in Fig. 16 as an example, the block performance of the host-allocated FE IF 110 is 3 GB / s x 4 = 12 GB / s.

[0110] The block performance requirement is 10 GB / s. The basic configuration backup block performance is the block performance of one FE IF 110 that performs backup processing in the basic configuration, and in this case is half the block performance of the FE IF 110 that performs only block processing. In other words, the value is 3 GB / s x 50% = 1.5 GB / s. Therefore, the sum of these is 11.5 GB / s, which is less than the 12 GB / s block performance of the host-allocated FE IF 110.

[0111] If the host-allocated FE IF block performance is equal to or greater than the sum of the block performance requirement and the basic configuration backup block performance (S804: NO), the management device 50 selects the basic configuration as the backup configuration to be set in the storage system 1 (S805).

[0112] If the host-allocated FE IF block performance is smaller than the sum of the block performance requirement and the basic configuration backup block performance (S804: YES), the management device 50 selects backup configuration 2 as the backup configuration to be set in the storage system 1 (S806).

[0113] After the backup configuration is determined, the management device 50 sets the backup configuration information of the FE IF pair that performs the backup process based on the determined backup configuration and the backup configuration management information T3 (S808).

[0114] As described above, this embodiment can determine an appropriate backup configuration based on the state of the storage system 1, that is, the network performance and the performance of the FE IF 110. Note that backup configuration 1, backup configuration 2, and one of the basic configurations may be excluded from the selection candidates. Furthermore, the judgment criteria may be omitted for the excluded backup configuration candidate. For example, if the basic configuration is excluded, steps S802 and S804 may be omitted. If backup configuration 1 is omitted, step S803 may be omitted, and a YES determination in step S802 may cause the flow to proceed to step S804. If backup configuration 2 is omitted, step S804 may be omitted, and a NO determination in step S803 may cause the basic configuration to be selected. [Example]

[0115] Another embodiment of this specification will be described below. This embodiment describes a method for selecting a backup configuration to be applied to the storage system 1 from among a plurality of backup configuration candidates. Specifically, an appropriate backup configuration is selected from the backup configuration described in embodiment 3 (Configuration 3 (third backup configuration)) and the backup configuration described in embodiment 4 (Configuration 4 (fourth backup configuration)).

[0116] Fig. 19 shows a flowchart of a backup configuration determination process according to Example 6. In this example, information to be referenced in determining and setting the backup configuration, which has the configuration described with reference to Figs. 16 and 17, is prepared in advance. In the following, an example will be described in which the management device 50 executes this process, but the entity that executes this process is not particularly limited.

[0117] The management device 50 references the configuration information (S801) and compares the distributed backup performance of backup configuration 3 with the WAN performance (S901). The distributed backup performance of backup configuration 3 is the product of the backup performance of the basic configuration and the number of FE IFs that execute backup processing. In this example, this value is twice the backup performance of the basic configuration.

[0118] If the distributed backup performance of backup configuration 3 is equal to or greater than the WAN performance (S901: NO), the management device 50 selects backup configuration 3 as the backup configuration to be set in the storage system 1 (S904).

[0119] If the distributed backup performance of backup configuration 3 is lower than the WAN performance (S901: NO), the management device 50 compares the host-allocated FE IF block performance with the value obtained by adding the basic configuration distributed backup block performance to the host performance requirement (S902).

[0120] The distributed backup block performance of configuration 3 is expressed as the product of the block performance per FE IF 110 that is executing the backup program P11 and the block protocol server program P15 and the number of those FE IFs 110. For example, the block performance per FE IF 110 is half the block performance of an FE IF 110 that executes only block processing, and there are two such FE IFs 110.

[0121] If the host-allocated FE IF block performance is smaller than the value obtained by adding the distributed backup block performance of configuration 3 to the host performance requirements (S902: YES), the management device 50 selects backup configuration 4 as the backup configuration to be set in the storage system 1 (S903). If not (S902: NO), the management device 50 selects backup configuration 3 as the backup configuration to be set in the storage system 1 (S904).

[0122] As described above, this embodiment can determine an appropriate backup configuration based on the state of the storage system 1, that is, the network performance and the performance of the FE IF 110. Note that backup configurations different from the above backup configurations 1 to 4 and the basic configuration may be prepared as selection candidates, and some of the above backup configurations may be excluded from the selection candidates. In embodiments 5 and 6, the device only determines the backup configuration, and its setting may be performed by another entity, and some of the judgment conditions may be omitted or other judgment conditions may be added.

[0123] The present invention is not limited to the above-described embodiments and includes various modifications. For example, the above-described embodiments have been described in detail to clearly explain the present invention, and the present invention is not necessarily limited to those including all of the described configurations. Furthermore, it is possible to replace part of the configuration of one embodiment with the configuration of another embodiment, or to add the configuration of another embodiment to the configuration of one embodiment. Furthermore, it is possible to add, delete, or replace part of the configuration of each embodiment with other configurations.

[0124] Furthermore, the above-mentioned components, functions, processing units, etc. may be realized in part or in whole by hardware, for example, by designing them as integrated circuits. Furthermore, the above-mentioned components, functions, etc. may be realized in software by a processor interpreting and executing a program that realizes each function. Information such as the programs, tables, and files that realize each function can be stored in memory, a storage device such as a hard disk or SSD, or a storage medium such as an IC card or SD card.

[0125] In addition, the control lines and information lines shown are those that are considered necessary for the explanation, and do not necessarily show all the control lines and information lines in the product. In reality, it can be assumed that almost all components are interconnected. [Explanation of symbols]

[0126] 1. Storage System 2. Kraut 3. WAN 30 Host Network 50 Management device 40 clients 60 Backup Network 100 Controllers 110 FE IF 111 Network I / F 112 Internal I / F 113 CPU 114 memory 116 Storage Devices P11 Backup Program P15 Block Protocol Server Program P17 Disability Response Program P51 Distributed backup instruction program P57 Disability Response Program T1 Backup Configuration Information T2 configuration decision information T3 Backup Configuration Management Information

Claims

1. An apparatus for determining a backup configuration of a storage system, comprising: a processor; a memory device; the storage system includes multiple front-end interfaces; the memory device stores configuration determination information; The configuration determination information is network performance information indicating the performance of a network between the storage system and a backup destination; interface performance information indicating the performance of the plurality of front-end interfaces; performance requirement information indicating a performance requirement for a host IO; The processor determines, based on the configuration determination information, a front-end interface that reads backup data from a storage device and a front-end interface that transmits the backup data to a backup destination.

2. 10. The apparatus of claim 1, The processor determines a backup configuration to be set from a plurality of backup configuration candidates; each of the plurality of backup configuration candidates indicates a front-end interface that reads the backup data and a front-end interface that transmits the backup data to a backup destination; the plurality of backup configuration candidates includes a first backup configuration; The first backup configuration comprises: a multiple host allocation front-end interface that executes host IO processing; a backup front-end interface that is excluded from the host IO processing and the reading of the backup data and that transmits the backup data to the backup destination; a backup data reading front-end interface that is excluded from the host IO processing and the processing of transmitting the backup data to the backup destination, and that reads the backup data.

3. 10. The apparatus of claim 1, The processor determines a backup configuration to be set from a plurality of backup configuration candidates; each of the plurality of backup configuration candidates indicates a front-end interface that reads the backup data and a front-end interface that transmits the backup data to a backup destination; the plurality of backup configuration candidates includes a second backup configuration; The second backup configuration is a multiple host allocation front-end interface that executes host IO processing; a backup front-end interface that is excluded from the host IO processing and the reading of the backup data, and that transmits the backup data to the backup destination; The backup front-end interface transmits the backup data read by the multiple host allocation front-end interface to the backup destination.

4. 10. The apparatus of claim 1, The processor determines a backup configuration to be set from a plurality of backup configuration candidates; each of the plurality of backup configuration candidates indicates a front-end interface that reads the backup data and a front-end interface that transmits the backup data to a backup destination; the plurality of backup configuration candidates include a first backup configuration and a base configuration; The first backup configuration comprises: a multiple host allocation front-end interface that executes host IO processing; a backup front-end interface that is excluded from the host IO processing and the reading of the backup data and that transmits the backup data to the backup destination; a backup data reading front-end interface that is excluded from the host IO processing and the processing of transmitting the backup data to the backup destination and that reads the backup data; The basic configuration is: a multiple host allocation front-end interface that executes host IO processing; a single basic backup front-end interface that is excluded from the host IO processing and that reads the backup data and transmits the backup data to the backup destination; The processor refers to the configuration determination information and If the backup performance of the basic configuration is equal to or greater than the bandwidth of the network to the backup destination, the basic configuration is selected; The device selects the first backup configuration when the backup performance of the basic configuration is smaller than the network bandwidth to the backup destination and the backup network bandwidth between front-end interfaces is larger than a predetermined performance requirement for backup.

5. 10. The apparatus of claim 1, The processor determines a backup configuration to be set from a plurality of backup configuration candidates; each of the plurality of backup configuration candidates indicates a front-end interface that reads the backup data and a front-end interface that transmits the backup data to a backup destination; the plurality of backup configuration candidates include a second backup configuration and a base configuration; The second backup configuration is a multiple host allocation front-end interface that executes host IO processing; a backup front-end interface that is excluded from the host IO processing and the reading of the backup data, and that transmits the backup data to the backup destination; the backup front-end interface transmits the backup data read by the multiple host allocation front-end interface to the backup destination; The basic configuration is: a multiple host allocation front-end interface that executes host IO processing; a single basic backup front-end interface that is excluded from the host IO processing and that reads the backup data and transmits the backup data to the backup destination; The processor refers to the configuration determination information and If the backup performance of the basic configuration is equal to or greater than the bandwidth of the network to the backup destination, the basic configuration is selected; A device that selects the second backup configuration when the backup performance of the basic configuration is smaller than the network bandwidth to the backup destination, and the value obtained by adding the performance requirements for the host IO processing to the data reading performance of the basic backup front-end interface is greater than the data reading performance of the multiple host-allocated front-end interface.

6. 10. The apparatus of claim 1, The processor determines a backup configuration to be set from a plurality of backup configuration candidates; each of the plurality of backup configuration candidates indicates a front-end interface that reads the backup data and a front-end interface that transmits the backup data to a backup destination; the plurality of backup configuration candidates include a first backup configuration and a second backup configuration; The first backup configuration comprises: a multiple host allocation front-end interface that executes host IO processing; a backup front-end interface that is excluded from the host IO processing and the reading of the backup data and that transmits the backup data to the backup destination; a backup data reading front-end interface that is excluded from the host IO processing and the processing of transmitting the backup data to the backup destination and that reads the backup data; The second backup configuration is a multiple host allocation front-end interface that executes host IO processing; a backup front-end interface that is excluded from the host IO processing and the reading of the backup data, and that transmits the backup data to the backup destination; In the second backup configuration, the backup front-end interface transmits the backup data read by the multiple host allocation front-end interface to the backup destination; The processor refers to the configuration determination information and Selecting the first backup configuration when the backup network bandwidth between the front-end interfaces is greater than a predetermined performance requirement for the backup; The apparatus selects the second backup configuration when the backup network bandwidth is equal to or less than a predetermined performance requirement for backup.

7. 10. The apparatus of claim 1, The processor determines a backup configuration to be set from a plurality of backup configuration candidates; each of the plurality of backup configuration candidates indicates a front-end interface that reads the backup data and a front-end interface that transmits the backup data to a backup destination; the plurality of backup configuration candidates include a first backup configuration, a second backup configuration, and a basic configuration; The first backup configuration comprises: a multiple host allocation front-end interface that executes host IO processing; a backup front-end interface that is excluded from the host IO processing and the reading of the backup data and that transmits the backup data to the backup destination; a backup data reading front-end interface that is excluded from the host IO processing and the processing of transmitting the backup data to the backup destination and that reads the backup data; The second backup configuration is a multiple host allocation front-end interface that executes host IO processing; a backup front-end interface that is excluded from the host IO processing and the reading of the backup data, and that transmits the backup data to the backup destination; In the second backup configuration, the backup front-end interface transmits the backup data read by the multiple host allocation front-end interface to the backup destination; The basic configuration is: a multiple host allocation front-end interface that executes host IO processing; a single basic backup front-end interface that is excluded from the host IO processing and that reads the backup data and transmits the backup data to the backup destination; The processor refers to the configuration determination information and If the backup performance of the basic configuration is equal to or greater than the bandwidth of the network to the backup destination, the basic configuration is selected; selects the first backup configuration when the backup performance of the basic configuration is smaller than the network bandwidth to the backup destination and the backup network bandwidth between front-end interfaces is larger than a predetermined performance requirement for backup; selects the second backup configuration when the backup performance of the basic configuration is smaller than the network bandwidth to the backup destination, the backup network bandwidth is equal to or smaller than the specified performance requirement for backup, and the value obtained by adding the data read performance of the basic backup front-end interface to the performance requirement for the host IO processing is greater than the data read performance of the multiple host allocated front-end interface, A device that selects the basic configuration when the backup performance of the basic configuration is smaller than the network bandwidth to the backup destination, the backup network bandwidth is less than the specified performance requirement for backup, and the value obtained by adding the data reading performance of the basic backup front-end interface to the performance requirement for the host IO processing is less than the data reading performance of the multiple host allocation front-end interface.

8. 3. The apparatus of claim 2, When a failure occurs in one of the backup front-end interface and the backup data read front-end interface, the other of the backup front-end interface and the backup data read front-end interface reads the backup data and transmits it to the backup destination.

9. 10. The apparatus of claim 1, The processor determines a backup configuration to be set from a plurality of backup configuration candidates; each of the plurality of backup configuration candidates indicates a front-end interface that reads the backup data and a front-end interface that transmits the backup data to a backup destination; the plurality of backup configuration candidates includes a third backup configuration; The third backup configuration is A plurality of host-allocated front-end interfaces for executing host IO processing, and a plurality of primary backup front-end interfaces; Each of the plurality of primary backup front-end interfaces: A device that is excluded from the host IO processing and that reads the backup data and transmits the backup data to the backup destination.

10. 10. The apparatus of claim 1, The processor determines a backup configuration to be set from a plurality of backup configuration candidates; each of the plurality of backup configuration candidates indicates a front-end interface that reads the backup data and a front-end interface that transmits the backup data to a backup destination; the plurality of backup configuration candidates includes a fourth backup configuration; The fourth backup configuration is A plurality of host-allocated front-end interfaces for executing host IO processing and a plurality of backup front-end interfaces are included; Each of the plurality of backup front-end interfaces An apparatus that is excluded from the host IO processing and the reading of the backup data, and that transmits the backup data read by a host-allocated front-end interface to the backup destination.

11. 10. The apparatus of claim 1, The processor determines a backup configuration to be set from a plurality of backup configuration candidates; each of the plurality of backup configuration candidates indicates a front-end interface that reads the backup data and a front-end interface that transmits the backup data to a backup destination; the plurality of backup configuration candidates include a third backup configuration and a fourth backup configuration; The third backup configuration is A plurality of host-allocated front-end interfaces for executing host IO processing, and a plurality of primary backup front-end interfaces; Each of the plurality of primary backup front-end interfaces: The host is excluded from the host IO processing, and executes reading of the backup data and transmission of the backup data to the backup destination. The fourth backup configuration is A plurality of host-allocated front-end interfaces for executing host IO processing and a plurality of backup front-end interfaces are included; In the fourth backup configuration, each of the multiple backup front-end interfaces: sending the backup data read by a host-allocated front-end interface that is excluded from the host IO processing and the reading of the backup data to the backup destination; The processor refers to the configuration determination information and If the backup performance of the third backup configuration is equal to or greater than the network performance to the backup destination, the third backup configuration is selected; selects the fourth backup configuration when the backup performance of the third backup configuration is lower than the network performance to the backup destination, and the value obtained by adding the data read performance of the multiple basic backup front-end interfaces to the performance requirement for the host IO processing is greater than the data read performance of the multiple host-allocated front-end interfaces; A device that selects the third backup configuration when the backup performance of the third backup configuration is smaller than the network performance to the backup destination, and the value obtained by adding the performance requirements for the host IO processing to the data reading performance of the multiple basic backup front-end interfaces is equal to or less than the data reading performance of the multiple host-allocated front-end interfaces.

12. 1. A method for determining a backup configuration for a storage system, comprising: the storage system includes multiple front-end interfaces; The method comprises: referencing configuration determination information, the configuration determination information including network performance information indicating the performance of a network between the storage system and a backup destination, interface performance information indicating the performance of the plurality of front-end interfaces, and performance requirement information indicating performance requirements for host IO; determining, based on the configuration determination information, a front-end interface that reads the backup data from the storage device and a front-end interface that transmits the backup data to a backup destination.