WO2017119116A1 - 統合プラットフォーム、サーバ、及び、フェイルオーバ方法 - Google Patents
統合プラットフォーム、サーバ、及び、フェイルオーバ方法 Download PDFInfo
- Publication number
- WO2017119116A1 WO2017119116A1 PCT/JP2016/050475 JP2016050475W WO2017119116A1 WO 2017119116 A1 WO2017119116 A1 WO 2017119116A1 JP 2016050475 W JP2016050475 W JP 2016050475W WO 2017119116 A1 WO2017119116 A1 WO 2017119116A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- boot
- efi
- server
- luid
- logical volume
- Prior art date
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/07—Responding to the occurrence of a fault, e.g. fault tolerance
- G06F11/16—Error detection or correction of the data by redundancy in hardware
- G06F11/20—Error detection or correction of the data by redundancy in hardware using active fault-masking, e.g. by switching out faulty elements or by switching in spare elements
- G06F11/202—Error detection or correction of the data by redundancy in hardware using active fault-masking, e.g. by switching out faulty elements or by switching in spare elements where processing functionality is redundant
- G06F11/2023—Failover techniques
- G06F11/2033—Failover techniques switching over of hardware resources
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/07—Responding to the occurrence of a fault, e.g. fault tolerance
- G06F11/16—Error detection or correction of the data by redundancy in hardware
- G06F11/20—Error detection or correction of the data by redundancy in hardware using active fault-masking, e.g. by switching out faulty elements or by switching in spare elements
- G06F11/202—Error detection or correction of the data by redundancy in hardware using active fault-masking, e.g. by switching out faulty elements or by switching in spare elements where processing functionality is redundant
- G06F11/2023—Failover techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/07—Responding to the occurrence of a fault, e.g. fault tolerance
- G06F11/16—Error detection or correction of the data by redundancy in hardware
- G06F11/20—Error detection or correction of the data by redundancy in hardware using active fault-masking, e.g. by switching out faulty elements or by switching in spare elements
- G06F11/202—Error detection or correction of the data by redundancy in hardware using active fault-masking, e.g. by switching out faulty elements or by switching in spare elements where processing functionality is redundant
- G06F11/2038—Error detection or correction of the data by redundancy in hardware using active fault-masking, e.g. by switching out faulty elements or by switching in spare elements where processing functionality is redundant with a single idle spare processing component
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/07—Responding to the occurrence of a fault, e.g. fault tolerance
- G06F11/16—Error detection or correction of the data by redundancy in hardware
- G06F11/20—Error detection or correction of the data by redundancy in hardware using active fault-masking, e.g. by switching out faulty elements or by switching in spare elements
- G06F11/202—Error detection or correction of the data by redundancy in hardware using active fault-masking, e.g. by switching out faulty elements or by switching in spare elements where processing functionality is redundant
- G06F11/2046—Error detection or correction of the data by redundancy in hardware using active fault-masking, e.g. by switching out faulty elements or by switching in spare elements where processing functionality is redundant where the redundant components share persistent storage
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/06—Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
- G06F3/0601—Interfaces specially adapted for storage systems
- G06F3/0602—Interfaces specially adapted for storage systems specifically adapted to achieve a particular effect
- G06F3/0614—Improving the reliability of storage systems
- G06F3/0617—Improving the reliability of storage systems in relation to availability
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/07—Responding to the occurrence of a fault, e.g. fault tolerance
- G06F11/14—Error detection or correction of the data by redundancy in operation
- G06F11/1479—Generic software techniques for error detection or fault masking
- G06F11/1482—Generic software techniques for error detection or fault masking by means of middleware or OS functionality
- G06F11/1484—Generic software techniques for error detection or fault masking by means of middleware or OS functionality involving virtual machines
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/07—Responding to the occurrence of a fault, e.g. fault tolerance
- G06F11/16—Error detection or correction of the data by redundancy in hardware
- G06F11/20—Error detection or correction of the data by redundancy in hardware using active fault-masking, e.g. by switching out faulty elements or by switching in spare elements
- G06F11/2097—Error detection or correction of the data by redundancy in hardware using active fault-masking, e.g. by switching out faulty elements or by switching in spare elements maintaining the standby controller/processing unit updated
Definitions
- the present invention relates generally to computer control, and more particularly to computer redundancy.
- LUs Logical Units
- the server may erroneously access an LU (for example, a logical volume (logical VOL)) that should not be accessed (I / O (Input / Output)) and update the data of the LU by mistake. is there.
- the LU masking function is known as a technology for restricting access to an LU to a specific server.
- This LU masking function creates an access control list for LUs for each port of the storage apparatus.
- the access control list includes a WWN (World Wide Name) of a physical port of FC-HBA (Fibre Channel-Host Bus Adapter) that is permitted to access the LU in the storage apparatus.
- WWN World Wide Name
- FC-HBA Fibre Channel-Host Bus Adapter
- the I / O ports (storage ports) of the storage device are conventionally as few as 1 to 2 ports, and access from a plurality of servers is possible using an FC switch.
- storage ports are often equipped with 10 or more ports, and it has become possible to connect directly to a plurality of servers without using expensive FC switches.
- the storage port and the physical port of the server are directly connected by an FC cable or a PCIe (Peripheral Component Interconnect Express) bus (in other words, the storage port and the physical port of the server have a one-to-one correspondence)
- the I / O request issued by the active server before switching and the I / O request issued by the spare server after switching are received at different storage ports.
- the spare server after switching sends out an LU search instruction based on the WWN of the storage port to which the I / O request is sent, but the WWN of the storage port that receives the I / O request has changed. Unable to find LU. Therefore, the spare server after switching cannot access the LU.
- an object of the present invention is to enable a spare server to boot normally when a failover is executed.
- An integrated platform includes active and spare servers and a storage device.
- the storage device has a plurality of storage ports, and a World Wide Name (WWN) is assigned to each of the plurality of storage ports.
- WWN World Wide Name
- Each of the plurality of logical volumes provided by the storage device is assigned a Logical Unit ID (LUID) that can be uniquely identified.
- the active server and the spare server are connected to the storage port on a one-to-one basis.
- the active server has boot search information that associates the WWN of the connection destination storage port, the logical unit number (LUN) of the boot logical volume that is a logical volume accessed at the time of booting, and the LUID of the boot logical volume. When failover is executed, the boot search information of the active server is copied to the spare server.
- LUN logical unit number
- the spare server when a failover is executed, the spare server can boot normally.
- a configuration example of an integrated platform is shown.
- An example of the server configuration is shown.
- 2 shows a configuration example of a storage apparatus.
- the structural example of a management server is shown.
- a reference example of Boot Order is shown.
- An example of Boot Order according to the present embodiment is shown.
- a configuration example of Boot Priority is shown.
- a configuration example of Boot Priority is shown.
- An example of the operation of failing over from the active server to the spare server is shown. It is a sequence chart which shows the boot operation example of an active server. It is a sequence chart which shows the boot operation example of the spare server after failover. It is a flowchart which shows the process example of the EFI driver which concerns on a present Example.
- At least one of “name” and “ID” may be used as an example of identification information of each information element, and these may be replaced with each other.
- “Boot Priority” is set as “Virtual Boot Priority” owned by virtual FC-HBA on LPAR
- “Boot Order” is set as guest on LPAR. It can be replaced as a “virtual boot order” owned by EFI.
- the name and reference symbol are used (for example, the server 100) when explaining without distinguishing the same type of element, and the identification assigned to the element when distinguishing and explaining the same type of element.
- Information for example, the servers 100A and 100B may be used.
- the process may be described with “program” as the subject, but the program performs the process defined by being executed by the processor using the memory and the communication port (communication control device). Therefore, the description of the processing may be a description of processing with the processor as the subject. Further, the processing disclosed with the program as the subject may be processing performed by a device (for example, a management system or a storage device) having a processor that executes the program. Further, part or all of the program may be realized by dedicated hardware. Various programs may be installed in each computer by a program distribution server or a storage medium.
- FIG. 1 shows a configuration example of an integrated platform according to this embodiment.
- the integrated platform 1 includes a storage device 200 and a plurality of servers 100.
- the storage apparatus 200 and the plurality of servers 100 are connected via a PCIe bus 46 so as to be capable of bidirectional communication.
- a plurality of servers 100 are mounted on the server chassis 15.
- the storage apparatus 200 and the plurality of servers 100 are connected to the management server 300 via the management network 45 so as to be capable of bidirectional communication.
- a management client 350 of the management server 300 and a service processor (SVP) 17 mounted on the server chassis 15 may be connected to the management network 45.
- the management network 45 may be a communication network such as a LAN (Local Area Network), for example.
- the server 100 may access the storage apparatus 200 based on the received I / O request. Access to the storage apparatus 200 may mean that the server 100 transmits an I / O request to the storage apparatus 200.
- An internal network (for example, LAN) 47 may exist inside the server chassis 15.
- the SVP 17 is an example of a controller, and manages each server 100 via the internal network 47.
- the SVP 16 may be able to issue a failover instruction to at least one of the switching source server 100 and the switching destination server 100.
- the SVP 17 may be connected to the maintenance port 16 inside the server chassis 15 via a circuit such as an internal bus so that bidirectional communication is possible.
- the administrator may be able to operate the SVP 17 without going through the management network 45 by directly connecting a maintenance terminal to the maintenance port 16 and using the maintenance terminal.
- the management server 300 is an example of a management system, and manages the computer system via the management network 45.
- the management server 300 may also be able to issue a failover instruction to at least one of the switching source server 100 and the switching destination server 100.
- each server 100 may be able to receive a failover instruction from at least one of the SVP 17 and the management server 30000.
- the SVP 17 can detect a predetermined event in the server chassis 15 and automatically perform a failover without an instruction from the management server 300, or can receive an instruction from the management server 300 (for example, In response to a manual operation by the operator (administrator) of the management client 350, failover can also be performed.
- the management client 350 is a computer that communicates with the GUI display processing module 32300 (see FIG. 4) of the management server 300 via the management network 45 and displays various information on the WEB browser.
- the administrator can manage the devices in the computer system by referring to the information displayed on the WEB browser on the management client.
- the management server 300 and the management client 350 may be composed of a single server.
- FIG. 2 shows a configuration example of the server 100.
- the server 100 includes a management port 11100 connected to the management network 45, a port 11000 connected to the internal network 47, one or more I / O ports 14000, and an FC connected to the storage apparatus 200 via a PCIe bus.
- the processor 12000 may be composed of one or more processors.
- the memory 13000 may be configured with one or more memories and may include a storage device such as an auxiliary storage device.
- the EFI 190 has a boot order 180, and the boot order 180 is used to access the logical VOL of the storage apparatus 200.
- the server 100 accesses the storage apparatus 200 via the FC-HBA 120.
- the FC-HBA 120 has a boot priority 150 used by the server 100 to access the logical VOL.
- the FC-HBA 120 also has an EFI driver 170 for initializing the FC-HBA 120 and accessing the storage apparatus 200.
- the memory 13000 may store an OS 13100, an LPAR management program 13200, an I / O port management table 13300, an LPAR management table 13400, and an LPAR operation schedule management table 13500.
- the LPAR management program 13200 logically divides physical resources (computer resources) such as the processor 12000 and the memory 13000 provided from the operating system 13100 to create an LPAR.
- the LPAR can also be called a management computer.
- the LPAR created by the LPAR management program 13200 recognizes a logical VOL on the storage apparatus 200 connected to the server 100 as a storage area via the PCIe bus 46000.
- the LPAR management program 13200 exists in the memory 13000, but the LPAR management program does not exist, and the storage area provided from the operating system 13100 is used to perform I / O on the storage area.
- the business application that performs That is, there may be a server 100 that cannot construct (execute) an LPAR.
- the LPAR management program 13200 exists in the memory 13000.
- a virtualization control program exists instead of the LPAR management program, and the virtualization control program is a physical resource such as the processor 12000 and the memory 13000. May be abstracted and standardized to provide virtual hardware to a virtual machine.
- LPAR corresponds to a virtual machine
- the virtualization control program corresponds to an LPAR management program.
- FIG. 3 shows a configuration example of the storage apparatus 200.
- the storage apparatus 200 is an example of a storage system, and includes a plurality of storage ports 21000, a management port 21100, a memory 23000, a RAID (Redundant Array of Inexpensive) Disks) group 24010, and a controller 25000. These elements are connected via a circuit such as an internal bus so that bidirectional communication is possible.
- a circuit such as an internal bus so that bidirectional communication is possible.
- the storage port 21000 may be connected to the server 100 via the PCIe bus 46.
- the management port 21100 may be connected to the management server 300 via the management network 45.
- the memory 23000 may store programs and management information.
- the memory 23000 may be composed of one or more memories and may include a storage device such as an auxiliary storage device.
- the RAID group 24010 may store various data.
- the controller 25000 may control data and management information in the memory.
- the memory 23000 includes a disk management program 23100, a port management table 23200, a host group management table 23300, a RAID group management table 23400, a volume management table 23500, a host group-volume related management table 23600, and a table size upper limit.
- the management table 23700 is stored.
- the disk management program 23100 communicates with the management server 300 via the management port 21100, and with respect to the management server 300, a port management table 23200, a host group management table 23300, a RAID group management table 23400, and a volume management table. 23500, the host group-volume association management table 23600, and the table size upper limit management table 23700, the information included in at least one table is provided to the storage apparatus 200.
- the RAID group 24010 includes a plurality of nonvolatile storage devices 24220. Instead of the RAID group 24010, one non-volatile storage device 24220 may be employed.
- a logical VOL 24110 is provided based on one or more nonvolatile storage devices 24220 such as a RAID group 24010. At least one logical VOL 24110 may be a virtual logical VOL such as a virtual volume according to Thin Provisioning.
- the controller 25000 may include a processor that controls the storage apparatus 200 and a cache memory that temporarily stores data exchanged with the server 100. Each controller 25000 may be interposed between the storage port 21000 and the RAID group 24010 to control data exchange between the two.
- the storage apparatus 200 receives an access request (pointing to an I / O request) specifying the logical VOL 24110 provided to the server 100, and transfers it to the logical VOL 24110 (for example, the storage device that is the basis of the logical VOL 24110).
- 3 and the above-described storage device that provides a storage area may be included in configurations other than those shown in FIG.
- a storage device that provides a storage controller and a storage area may be stored in a separate housing.
- the memory 23000 and the controller 25000 may be storage controllers.
- the storage apparatus may be called a storage system.
- the storage system may be a plurality of storage devices.
- FIG. 4 shows a configuration example of the management server 300.
- the management server 300 is an example of a management system, and includes a management port 31000 for connection to the management network 45, a processor 31100, a storage resource 33000, and an output device 31200 such as a display device for outputting processing results to be described later. And an input device 31300 such as a keyboard for an administrator to input instructions. These elements are connected to each other via a circuit such as an internal bus so that bidirectional communication is possible.
- the storage resource 33000 may be one or more memories (for example, semiconductor memories), or may include a mixture of nonvolatile storage devices.
- the storage resource 33000 stores a management program 32000.
- the management program 32000 may include a device management module 32100, a device communication module 32200, and a GUI display processing module 32300.
- Each module is provided as a program module of the storage resource 33000, but may be provided as a hardware module.
- the management program 32000 may not be configured by modules as long as the processing of each module can be realized. That is, the description of each module in the following description may be replaced with the description related to the management program 32000.
- the storage resource 33000 may further store a device management table 33200, a host-storage path management table 33300, and a configuration table 93400.
- the configuration table 93400 may store configuration information.
- the configuration information includes, for example, each item of the I / O port management table 13300 collected from each server 100 managed by the device communication module 32200, each item of the LPAR management table 13400, and each item of the LPAR operation schedule management table 13500. Items, each item of the port management table 23200 collected from each managed storage, each item of the host group management table 23300, each item of the RAID group management table 23400, each item of the volume management table 23500, Each item of the host group-volume related management table 23600 and each item of the table size upper limit management table 23700 may be included.
- the configuration table 93400 may not necessarily store all the tables of the management target device or all the items in the table.
- the data representation format and data structure of each item stored in the configuration table 93400 may not be the same as that of the management target device.
- the management program 32000 may receive each item in the data structure or data representation format of the management target device.
- the device communication module 32200 periodically or repeatedly accesses the managed device under management, and acquires configuration information of each component in the managed device. Note that the repetition of the execution instruction does not have to be strictly every fixed period, and may be at any timing.
- the device communication module 32200 may instruct the managed device under management to change the configuration in response to a request from the administrator. After instructing the management target device to change the configuration, the device communication module 32200 reacquires the configuration information of each component in the management target device and keeps the configuration information stored in the configuration table 93400 up to date. Good.
- the GUI display processing module 32300 displays the acquired configuration management information via the output device 31200 in response to a request from the administrator via the input device 31300.
- the input device and the output device may be separate devices, or may be one or more integrated devices.
- the management server may have, for example, a display, a keyboard, a pointer device, etc. as input / output devices, or may have other devices.
- a serial interface or an Ethernet interface may be used as an alternative to the input / output device, and a display computer (eg, management client 35000) having a display, a keyboard, and / or a pointer device may be connected to the interface.
- the management server transmits the display information to the display computer via the interface, receives the input information from the display computer, displays the input information on the display computer, or accepts the input.
- the input and display at the input / output device may be substituted.
- a set of one or more computers that manage a computer system (information processing system) and display display information can be referred to as a “management system”.
- a management computer that displays display information on a display device or a remote display computer can be called a management system, and a combination of a management computer and a display computer (for example, the management client 35000 in FIG. 1) can also be called a management system. it can.
- a plurality of computers may realize processing equivalent to that of the management computer.
- a plurality of computers are referred to as a management system. be able to.
- FIG. 5 shows a reference example of Boot Order.
- the Boot Order is a table for managing the priority of the Device Path used by the server.
- the Boot Order may be composed of a description that the user describes in an arbitrary expression and a device path that indicates the location of the device to boot.
- the description of Device Path is defined in the UEFI specification, and may be generated by an EFI or EFI driver.
- Boot Order may be referred to as boot order information.
- Each entry of Boot Order may be referred to as a Boot Option.
- FIG. 5 is an example in which Boot Order's Device Path is configured with the WWN assigned to the Fiber Channel as a key.
- FIG. 6 shows an example of Boot Order 1800 according to the present embodiment.
- the Device Path of Boot Order 1800 is based on a GUID that a vendor assigns an arbitrary number in place of a WWN assigned to a Fiber Channel as shown in FIG. 5 and a LUID assigned to an LU (for example, a logical VOL). Composed.
- VenMsg (Vender GUID, LUID # C)” in FIG. 6 is expressed as “LUID # C”.
- “HD (1, MBR, 0xA06A915F, 0x800, 0xAF000)” of Device Path in FIG. 6 is represented as “LUN # z”.
- the Device Path is used when the EFI driver 170 searches for a device, and may be a description different for each EFI driver 170.
- the Boot Order 1800 in FIG. 6 indicates “FC1”, “FC2”, and “FC3” in descending order of priority.
- the system referring to Boot Order in FIG. 6 tries to start from the Device Path of “FC1” of the entry “1”, and when it fails, next, it tries to start from the Device Path of “FC2” of the entry “2”. Repeat that.
- FIG. 5 and 6 are both descriptions that satisfy the UEFI specification, and are typically used in the notation of FIG. However, in this embodiment, the notation shown in FIG. 6 is used.
- FIG. 7 and 8 show a configuration example of the boot priority 1500 included in the FC-HBA 120.
- FIG. 7 and 8 show a configuration example of the boot priority 1500 included in the FC-HBA 120.
- the Boot Priority 1500 may have, as item values, the WWN of the storage device I / O port, the LUN of the storage device, and the LUID assigned to the logical VOL of the storage device.
- the LUID is a unique ID for a plurality of logical VOLs existing in a plurality of storage apparatuses. For example, in FIG. 9, even when logical VOLs of different storage apparatuses are assigned to the active server and the spare server, the LUIDs of the respective logical VOLs do not overlap.
- Boot Priority 1500 may be referred to as boot search information.
- the item value of Boot Priority 1500 may be set by the user.
- the EFI driver 170 may provide an interface for setting and changing the item value of the Boot Priority 1500.
- the Boot Priority 1500 is used by the EFI driver 170 to respond with a priority to a device search instruction received from the EFI 190.
- the LUID is such that the EFI driver 170 issues an Inquiry command requesting the Device Identification VPD Page to the storage device, and the Identifier Type or Identity Authentication from the information in the Identification Description list that is returned, , T10 Vendor Identification shows the value of Identification Descriptor.
- FIG. 9 shows an example of the operation of switching from the active server to the spare server when a failure occurs in the redundant system.
- the SVP copies the Boot Order 1800C included in the EFI 190 of the active server 100 to the EFI 190B of the spare server 100B as a failover process (the post order is referred to as Boot Order 1800D).
- the SVP also copies the Boot Priority 1500C of the current FC-HBA 120A to the spare FC-HBA 120B (the copy is referred to as Boot Priority 1500D).
- FIG. 10 shows an example of the boot operation of the active server 100A
- FIG. 11 shows an example of the boot operation of the standby server 100C after failover.
- FIG. 10 is a sequence chart showing an example of the boot operation of the active server 100A in FIG.
- Device Path including LUID # C is set in the entry “1” of Boot Order 1800C of the active server 100A.
- WWN # 1, LUN # z, and LUID # C are set in the entry “1” of the Boot Priority 1500C of the EFI driver 170A.
- the EFI 190A and the EFI driver 170A start up in cooperation.
- the EFI 190A first reads the Device Path of the entry “1” of the Boot Order 1800C (S40100), and issues an execution instruction to the EFI driver 170A (S40300). This execution instruction may include LUID # C described in the read Device Path. Then, the EFI 190A waits for completion of the execution of the EFI driver 170A (S40400).
- the EFI driver 170A confirms that WWN # 1, LUN # z, and LUID # C are set in the entry “1” of the Boot Priority 1500C (S40200), and waits for the EFI 190A to be called (S40500). .
- the EFI driver 190A When the EFI driver 190A receives an execution instruction from the EFI 190A, the EFI driver 190A specifies WWN # 1 and LUN # z corresponding to the LUID # C included in the execution instruction from the Boot Priority 1500C. Then, the EFI driver 190A searches for the logical VOL of LUN # z using the identified WWN # 1 as a key (S40600).
- the EFI driver 170A can find a logical VOL of LUN # z using the WWN # 1 as a key.
- the EFI driver 170A transmits the Device Path described using the found logical VOL LUID # C to the EFI 190A (S40700).
- the EFI 190A compares the Device Path transmitted from the EFI driver 170A with the Device Path for which the execution instruction has been issued in S40300 (S40800).
- FIG. 11 is a sequence chart showing an example of the boot operation of the spare server 100B after failover in FIG.
- the EFI 190B and the EFI driver 170B start up in cooperation.
- EFI190B Boot Order1800D is a copy of EFI190A Boot Order1800C.
- boot priority 1500D of the FC-HBA 120B is a copy of the boot priority 1500C of the FC-HBA 120A.
- the EFI 190B first reads the Device Path of the entry “1” of Boot Order 1800D (S50100), and issues an execution instruction to the EFI driver 170B (S50300). This execution instruction may include LUID # C described in the Device Path. Then, the EFI 190B waits for completion of the execution of the EFI driver 170B (S50400).
- the EFI driver 170B confirms that WWN # 1, LUN # z, and LUID # C are set in the entry “1” of the Boot Priority 1500D (S50200), and waits for the EFI 190B to be called (S50500). .
- the EFI driver 170B When the execution instruction is received from the EFI 190B, the EFI driver 170B specifies WWN # 1 and LUN # z corresponding to the LUID # C included in the execution instruction from the Boot Priority 1500D. Then, the EFI driver 170B searches for the logical VOL of the specified WWN # 1 and LUN # z (S50600).
- the EFI driver 170B cannot find a logical VOL of LUN # z using the WWN # 1 as a key (S50700).
- the EFI driver 170B next searches for a logical VOL of LUN # z using LUID # C as a key (S50800).
- the EFI driver 170B can find the logical VOL of LUN # z using LUID # C as a key. Then, the EFI driver 170B recognizes that the path to the logical VOL of the LUN #z is WWN # 2 (S50900).
- the EFI driver 170B rewrites WWN # 1 of the entry “1” of Boot Priority 1500D to WWN # 2 (S51000). By this rewriting, the logical VOL of LUN # z can be immediately discovered from the next time using WWN # 2 corresponding to LUID # C as a key, as in FIG.
- the EFI driver 170B transmits the Device Path described using the discovered logical VOL LUID # C to the EFI 190B (S51100).
- the EFI 190B compares the Device Path transmitted from the EFI driver 170B with the Device Path for which the execution instruction has been issued in S40300 (S51200).
- FIG. 12 is a flowchart illustrating a processing example of the EFI driver 170 according to the present embodiment.
- the EFI driver 170A of the working FC-HBA 120A may perform the processing of FIG. 12 in S40600 of FIG. 10, and the EFI driver 170B of the spare FC-HBA 120B may perform the processing of FIG. 12 in S50600, S50700, S50800, and S50900 of FIG.
- the EFI driver 170 initializes a variable n (n is an integer) for managing the maximum number of entries (for example, “8”) of the Boot Priority 1500 to “1” (S70100).
- the EFI driver 170 confirms the nth entry of the Boot Priority 1500 (S70200).
- the EFI driver 170 searches for a logical VOL that matches the WWN and LUN set in the nth entry (S70400). Then, the process proceeds to S70500.
- the EFI driver 170 stores the Device Path described using the LUID of the found logical VOL in the Boot Order 1800 (S71100). Then, the EFI driver 170 increments the variable n by 1 (S71000), and proceeds to S71200.
- the EFI driver 170 stores the Device Path described using the LUID of the found logical VOL in the Boot Order 1800 (S71100). Then, the EFI driver 170 increments the variable n by 1 (S71000), and proceeds to S71200.
- the EFI driver 170 ends the logical VOL search when n is larger than 8 (n ⁇ 8: NO), and returns to S70200 when n is 8 or less (n ⁇ 8: YES). Continue searching for VOL.
- S40600 in FIG. 10 corresponds to the processing when the logical VOL having the same WWN and LUN is found in S70500 in the processing of FIG.
- S50600, S50700, S50800, and S50900 in FIG. 11 correspond to the processing when the logical volume with the same WWN and LUN is not found in S70500 and the logical VOL with the same LUID is found in S70800 in the processing of FIG. .
- the spare server 100B can be normally started. If the Boot Order is described as in the example of FIG. 5, the spare server cannot find a logical VOL in S50700 and fails to start.
- a logical VOL is searched using WWN as a key, and if it is not found by the search, a logical VOL is searched using LUID as a key. This is because the search can be performed faster (that is, the boot time is shorter) than using as a key. Therefore, in this embodiment, as shown in FIGS. 7 and 8, when a logical VOL is found using the LUID as a key, the WWN of the Boot Priority 1500 is updated to the WWN on the path to the found logical VOL. The next boot time is shortened.
- Integrated platform 100 Server 120: FC-HBA 200: Storage device 190: EFI 170: EFI driver 1500: Boot Priority 1800: Boot Order
Abstract
Description
ストレージ装置は、複数のストレージポートを有し、当該複数のストレージポートには、それぞれ、World Wide Name(WWN)が付与されている。
ストレージ装置が提供する複数の論理ボリュームには、それぞれ、一意に識別可能なLogical Unit ID(LUID)が付与されている。
現用及び予備サーバは、それぞれ、ストレージポートと1対1で接続されている。
現用サーバは、接続先のストレージポートのWWNと、ブート時にアクセスする論理ボリュームであるブート論理ボリュームのLogical Unit Number(LUN)と、当該ブート論理ボリュームのLUIDと、を関連付けるブート検索情報、を有する。
フェイルオーバが実行される際、現用サーバが有するブート検索情報は、予備サーバへコピーされる。
Claims (9)
- 現用及び予備サーバと、ストレージ装置とを有する統合プラットフォームであって、
前記ストレージ装置は、複数のストレージポートを有し、当該複数のストレージポートには、それぞれ、World Wide Name(WWN)が付与されており、
前記ストレージ装置が提供する複数の論理ボリュームには、それぞれ、一意に識別可能なLogical Unit ID(LUID)が付与されており、
前記現用及び予備サーバは、それぞれ、ストレージポートと1対1で接続されており、
前記現用サーバは、接続先のストレージポートのWWNと、ブート時にアクセスする論理ボリュームであるブート論理ボリュームのLogical Unit Number(LUN)と、当該ブート論理ボリュームのLUIDと、を関連付けるブート検索情報、を有し、
フェイルオーバが実行される際、前記現用サーバが有するブート検索情報は、前記予備サーバへコピーされる
統合プラットフォーム。 - 前記現用及び予備サーバは、それぞれ、Extensible Firmware Interface(EFI)部と、EFIドライバ部とを含み、
前記EFI部は、EFIの仕様に準拠し、前記ブート論理ボリュームへのデバイスパス情報を含むブート順序情報を有し、前記デバイスパス情報は、LUIDを用いて記述されており、
前記EFIドライバ部は、前記ブート検索情報を有し、
フェイルオーバが実行される際、前記現用サーバのEFI部が有するブート検索情報は、前記予備サーバのEFI部へコピーされ、前記現用サーバのEFIドライバ部が有する前記ブート順序情報は、前記予備サーバのEFIドライバ部へコピーされる
請求項1に記載の統合プラットフォーム。 - 前記EFI部は、前記ブート順序情報のデバイスバス情報に含まれるLUIDを、前記EFIドライバ部へ発行し、
前記EFIドライバ部は、
前記ブート検索情報において、前記EFIから発行されたLUIDと関連付けられているWWNを用いて、前記ブート論理ボリュームを検索し、
その検索の結果、前記ブート論理ボリュームを発見できない場合、当該ブート検索情報において、前記EFIから発行されたLUIDを用いて、前記ブート論理ボリュームを検索する
請求項2に記載の統合プラットフォーム。 - 前記EFIドライバ部は、
前記EFIから発行されたLUIDを用いた前記ブート論理ボリュームの検索の結果、前記ブート論理ボリュームを発見できた場合、前記ブート検索情報において、前記LUIDと関連付けられているWWNを、そのブート論理ボリュームを発見できた経路上のストレージポートのWWNに変更する
請求項3に記載の統合プラットフォーム。 - 前記EFIドライバ部は、
前記ブート論理ボリュームを発見できた場合、そのブート論理ボリュームへのLUIDを含むデバイスパス情報を、前記EFI部へ返し、
前記EFI部は、
前記EFIドライバ部へ発行したLUIDを含むデバイスパス情報と、前記EFIドライバ部から返されたLUIDを含むデバイスパス情報が一致する場合、当該デバイスパス情報の示すブート論理ボリュームからブートを開始する
請求項4に記載の統合プラットフォーム。 - ストレージ装置と接続されているサーバであって、
前記ストレージ装置は、複数のストレージポートを有し、当該複数のストレージポートには、それぞれ、World Wide Name(WWN)が付与されており、
前記ストレージ装置が提供する複数の論理ボリュームには、それぞれ、一意に識別可能なLogical Unit ID(LUID)が付与されており、
前記サーバは、ストレージポートと1対1で接続されており、
前記サーバは、接続先のストレージポートのWWNと、ブート時にアクセスする論理ボリュームであるブート論理ボリュームのLogical Unit Number(LUN)と、当該ブート論理ボリュームのLUIDと、を関連付けるブート検索情報、を有し、
フェイルオーバが実行される際、前記サーバが有するブート検索情報は、他のサーバへコピーされる
サーバ。 - 前記サーバは、Extensible Firmware Interface(EFI)部と、EFIドライバ部とを含み、
前記EFI部は、EFIの仕様に準拠し、前記ブート論理ボリュームへのデバイスパス情報を含むブート順序情報を有し、前記デバイスパス情報は、LUIDを用いて記述されており、
前記EFIドライバ部は、前記ブート検索情報を有し、
フェイルオーバが実行される際、前記サーバのEFI部が有するブート検索情報は、前記他のサーバのEFI部へコピーされ、前記サーバのEFIドライバ部が有する前記ブート順序情報は、前記他のサーバのEFIドライバ部へコピーされる
請求項6に記載のサーバ。 - ストレージ装置に接続されている現用サーバ及び予備サーバ間におけるフェイルオーバ方法であって、
前記ストレージ装置は、複数のストレージポートを有し、当該複数のストレージポートには、それぞれ、World Wide Name(WWN)が付与されており、
前記ストレージ装置が提供する複数の論理ボリュームには、それぞれ、一意に識別可能なLogical Unit ID(LUID)が付与されており、
前記現用及び予備サーバは、それぞれ、ストレージポートと1対1で接続されており、
前記現用サーバは、接続先のストレージポートのWWNと、ブート時にアクセスする論理ボリュームであるブート論理ボリュームのLogical Unit Number(LUN)と、当該ブート論理ボリュームのLUIDと、を関連付けるブート検索情報、を有し、
前記現用サーバから前記予備サーバに対してフェイルオーバを実行する際、前記現用サーバが有するブート検索情報を、前記予備サーバにコピーする
フェイルオーバ方法。 - 前記現用及び予備サーバは、それぞれ、Extensible Firmware Interface(EFI)部と、EFIドライバ部とを含み、
前記EFI部は、EFIの仕様に準拠し、前記ブート論理ボリュームへのデバイスパス情報を含むブート順序情報を有し、前記デバイスパス情報は、LUIDを用いて記述されており、
前記EFIドライバ部は、前記ブート検索情報を有し、
前記フェイルオーバを実行する際、前記現用サーバのEFI部が有するブート検索情報を、前記予備サーバのEFI部にコピーし、前記現用サーバのEFIドライバ部が有する前記ブート順序情報を、前記予備サーバのEFIドライバ部にコピーする
請求項8に記載のフェイルオーバ方法。
Priority Applications (3)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
PCT/JP2016/050475 WO2017119116A1 (ja) | 2016-01-08 | 2016-01-08 | 統合プラットフォーム、サーバ、及び、フェイルオーバ方法 |
JP2017560003A JP6516875B2 (ja) | 2016-01-08 | 2016-01-08 | 統合プラットフォーム、サーバ、及び、フェイルオーバ方法 |
US15/761,116 US10579486B2 (en) | 2016-01-08 | 2016-01-08 | Integrated platform, server and failover method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
PCT/JP2016/050475 WO2017119116A1 (ja) | 2016-01-08 | 2016-01-08 | 統合プラットフォーム、サーバ、及び、フェイルオーバ方法 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2017119116A1 true WO2017119116A1 (ja) | 2017-07-13 |
Family
ID=59273390
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/JP2016/050475 WO2017119116A1 (ja) | 2016-01-08 | 2016-01-08 | 統合プラットフォーム、サーバ、及び、フェイルオーバ方法 |
Country Status (3)
Country | Link |
---|---|
US (1) | US10579486B2 (ja) |
JP (1) | JP6516875B2 (ja) |
WO (1) | WO2017119116A1 (ja) |
Families Citing this family (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US11150911B2 (en) * | 2018-06-15 | 2021-10-19 | Dell Products, L.P. | System and method for managing UEFI boot device path based on custom selection |
CN116661688B (zh) * | 2023-05-23 | 2023-12-12 | 无锡众星微系统技术有限公司 | 一种sas存储系统的业务响应方法和装置 |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2001175626A (ja) * | 1999-12-22 | 2001-06-29 | Toshiba Corp | 最後に処理を行っていたサーバ計算機を判定するプログラムを記録した記録媒体、及び高可用性計算機システム |
JP2013089148A (ja) * | 2011-10-21 | 2013-05-13 | Hitachi Ltd | 計算機システムおよび計算機システムにおけるモジュール引き継ぎ方法 |
JP2015060474A (ja) * | 2013-09-20 | 2015-03-30 | 日本電気株式会社 | 情報処理引き継ぎ制御装置、情報処理引き継ぎ制御方法、及び、情報処理引き継ぎ制御プログラム |
Family Cites Families (22)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5146568A (en) * | 1988-09-06 | 1992-09-08 | Digital Equipment Corporation | Remote bootstrapping a node over communication link by initially requesting remote storage access program which emulates local disk to load other programs |
US6343324B1 (en) * | 1999-09-13 | 2002-01-29 | International Business Machines Corporation | Method and system for controlling access share storage devices in a network environment by configuring host-to-volume mapping data structures in the controller memory for granting and denying access to the devices |
US6931519B1 (en) * | 2000-08-25 | 2005-08-16 | Sun Microsystems, Inc. | Method and apparatus for reliable booting device |
US7421478B1 (en) * | 2002-03-07 | 2008-09-02 | Cisco Technology, Inc. | Method and apparatus for exchanging heartbeat messages and configuration information between nodes operating in a master-slave configuration |
US7039829B2 (en) * | 2002-11-07 | 2006-05-02 | Lsi Logic Corporation | Apparatus and method for enhancing data availability by implementing inter-storage-unit communication |
US7340638B2 (en) * | 2003-01-30 | 2008-03-04 | Microsoft Corporation | Operating system update and boot failure recovery |
US7676600B2 (en) * | 2003-04-23 | 2010-03-09 | Dot Hill Systems Corporation | Network, storage appliance, and method for externalizing an internal I/O link between a server and a storage controller integrated within the storage appliance chassis |
JP4462024B2 (ja) * | 2004-12-09 | 2010-05-12 | 株式会社日立製作所 | ディスク引き継ぎによるフェイルオーバ方法 |
US8924499B2 (en) * | 2004-12-14 | 2014-12-30 | International Business Machines Corporation | Operating system migration with minimal storage area network reconfiguration |
US7721138B1 (en) * | 2004-12-28 | 2010-05-18 | Acronis Inc. | System and method for on-the-fly migration of server from backup |
US8006125B1 (en) * | 2005-04-29 | 2011-08-23 | Microsoft Corporation | Automatic detection and recovery of corrupt disk metadata |
JP4710518B2 (ja) * | 2005-09-28 | 2011-06-29 | 株式会社日立製作所 | 計算機システムとそのブート制御方法 |
JP4544146B2 (ja) * | 2005-11-29 | 2010-09-15 | 株式会社日立製作所 | 障害回復方法 |
US7627584B2 (en) * | 2005-11-30 | 2009-12-01 | Oracle International Corporation | Database system configured for automatic failover with no data loss |
US8705344B2 (en) * | 2006-11-14 | 2014-04-22 | Cisco Technology, Inc. | Graceful failover of a principal link in a fiber-channel fabric |
US7945773B2 (en) * | 2007-09-18 | 2011-05-17 | International Business Machines Corporation | Failover of blade servers in a data center |
US8774052B2 (en) * | 2011-02-24 | 2014-07-08 | Brocade Communications Systems, Inc. | Virtual port world wide names |
US8707085B2 (en) * | 2011-06-30 | 2014-04-22 | International Business Machines Corporation | High availability data storage systems and methods |
US8626967B1 (en) * | 2012-06-29 | 2014-01-07 | Emc Corporation | Virtualization of a storage processor for port failover |
JP5856925B2 (ja) | 2012-08-21 | 2016-02-10 | 株式会社日立製作所 | 計算機システム |
CN104798349B (zh) * | 2013-01-30 | 2018-08-07 | 慧与发展有限责任合伙企业 | 响应于端口故障的故障转移 |
US9747180B1 (en) * | 2015-03-31 | 2017-08-29 | EMC IP Holding Company LLC | Controlling virtual endpoint failover during administrative SCSI target port disable/enable |
-
2016
- 2016-01-08 US US15/761,116 patent/US10579486B2/en active Active
- 2016-01-08 JP JP2017560003A patent/JP6516875B2/ja active Active
- 2016-01-08 WO PCT/JP2016/050475 patent/WO2017119116A1/ja active Application Filing
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2001175626A (ja) * | 1999-12-22 | 2001-06-29 | Toshiba Corp | 最後に処理を行っていたサーバ計算機を判定するプログラムを記録した記録媒体、及び高可用性計算機システム |
JP2013089148A (ja) * | 2011-10-21 | 2013-05-13 | Hitachi Ltd | 計算機システムおよび計算機システムにおけるモジュール引き継ぎ方法 |
JP2015060474A (ja) * | 2013-09-20 | 2015-03-30 | 日本電気株式会社 | 情報処理引き継ぎ制御装置、情報処理引き継ぎ制御方法、及び、情報処理引き継ぎ制御プログラム |
Also Published As
Publication number | Publication date |
---|---|
JPWO2017119116A1 (ja) | 2018-05-31 |
US20180260289A1 (en) | 2018-09-13 |
JP6516875B2 (ja) | 2019-05-22 |
US10579486B2 (en) | 2020-03-03 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US7346800B2 (en) | Fail over method through disk take over and computer system having failover function | |
US8015396B2 (en) | Method for changing booting configuration and computer system capable of booting OS | |
WO2015162660A1 (ja) | 計算機システム | |
JP4448878B2 (ja) | 障害回復環境の設定方法 | |
US9886284B2 (en) | Identification of bootable devices | |
US20070237162A1 (en) | Method, apparatus, and computer product for processing resource change | |
WO2012004902A1 (ja) | 計算機システム及び計算機システムの系切替制御方法 | |
US20140244822A1 (en) | Management apparatus and method of managing server node | |
JP2010257274A (ja) | 仮想化環境におけるストレージ管理システム及びストレージ管理方法 | |
JP5316616B2 (ja) | 業務引き継ぎ方法、計算機システム、及び管理サーバ | |
WO2017119116A1 (ja) | 統合プラットフォーム、サーバ、及び、フェイルオーバ方法 | |
JP5267544B2 (ja) | ディスク引き継ぎによるフェイルオーバ方法 | |
KR101436101B1 (ko) | 사용자 단말의 저장 장치를 대체하는 서비스를 제공하는 서버 장치 및 그 방법 | |
JP5750169B2 (ja) | 計算機システム、プログラム連携方法、及びプログラム | |
KR101849708B1 (ko) | 사용자 단말의 저장 장치를 대체하는 서비스를 제공하는 서버 장치 및 그 방법 | |
JP4877368B2 (ja) | ディスク引き継ぎによるフェイルオーバ方法 | |
Guide | VMware, Inc. | |
US20140189129A1 (en) | Information processing system and storage apparatus | |
WO2016056050A1 (ja) | 計算機システム及びそれの管理システム |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 16883619 Country of ref document: EP Kind code of ref document: A1 |
|
ENP | Entry into the national phase |
Ref document number: 2017560003 Country of ref document: JP Kind code of ref document: A |
|
WWE | Wipo information: entry into national phase |
Ref document number: 15761116 Country of ref document: US |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 16883619 Country of ref document: EP Kind code of ref document: A1 |