CN113448802B - Method, device, system and server for synchronizing states of hard disks - Google Patents
Method, device, system and server for synchronizing states of hard disks Download PDFInfo
- Publication number
- CN113448802B CN113448802B CN202110710336.7A CN202110710336A CN113448802B CN 113448802 B CN113448802 B CN 113448802B CN 202110710336 A CN202110710336 A CN 202110710336A CN 113448802 B CN113448802 B CN 113448802B
- Authority
- CN
- China
- Prior art keywords
- management controller
- controller
- management
- hard disk
- server
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 24
- 230000003993 interaction Effects 0.000 claims description 23
- 238000012544 monitoring process Methods 0.000 claims description 6
- 238000005192 partition Methods 0.000 claims description 4
- 238000010586 diagram Methods 0.000 description 4
- 238000012423 maintenance Methods 0.000 description 4
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000001514 detection method Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/30—Monitoring
- G06F11/3003—Monitoring arrangements specially adapted to the computing system or computing system component being monitored
- G06F11/3034—Monitoring arrangements specially adapted to the computing system or computing system component being monitored where the computing system component is a storage system, e.g. DASD based or network based
-
- 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
- G06F11/30—Monitoring
- G06F11/32—Monitoring with visual or acoustical indication of the functioning of the machine
- G06F11/324—Display of status information
- G06F11/327—Alarm or error message display
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Quality & Reliability (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Hardware Redundancy (AREA)
Abstract
The specification provides a hard disk state synchronization method, device and system and a server, and relates to the technical field of communication. A hard disk state synchronization method, comprising: through the connected exchange equipment, the exchange of state messages is carried out with a management controller of the opposite terminal server; if the state message sent by the management controller of the opposite terminal server is not received within a preset time interval and the state message is configured as a standby management controller, sending an alarm message to the management device connected with the server and the opposite terminal server, and sending a switching message to the expansion controller in the storage device, wherein the switching message is used for notifying the expansion controller to modify the established first corresponding relation between the management controller of the opposite terminal server and the managed hard disk into a second corresponding relation between the management controller of the opposite terminal server and the managed hard disk; based on the second corresponding relation, the state information of the managed hard disk is obtained, and the running state of the managed hard disk is determined through the state information.
Description
Technical Field
The present disclosure relates to the field of communications technologies, and in particular, to a method, an apparatus, a system, and a server for synchronizing states of hard disks.
Background
The baseboard management controller (Baseboard Management Controller, abbreviated as BMC) is a common microprocessor on a server, has a SAS (serial attached small computer system interface ) storage network management function, and can be provided with a BMC, a storage control card, an expansion controller and a plurality of hard disks in the server, wherein the BMC is communicated with the storage control card, and the expansion controller is inserted with the hard disks and is connected with the storage control card.
In the working process, the BMC needs to acquire the running state of each hard disk through the storage control card so as to monitor the hard disk in the server. However, due to the limitation of the structure of the server, once the BMC or the storage control card fails, access to the hard disk cannot be realized, and a worker cannot acquire the running state of the hard disk, so that management and maintenance of the server are difficult to execute, and the reliability of the storage system is reduced.
Disclosure of Invention
In order to overcome the problems in the related art, the present specification provides a method, an apparatus, a system, and a server for synchronizing states of a hard disk.
With reference to the first aspect of the embodiments of the present specification, the present application provides a method for synchronizing states of a hard disk, which is applied to a management controller of a server, and includes:
through the connected exchange equipment, the exchange equipment interacts with a management controller of the opposite terminal server, wherein the state message carries state information of a managed hard disk in the storage equipment;
if the state message sent by the management controller of the opposite terminal server is not received within a preset time interval and the state message is configured as a standby management controller, sending an alarm message to the management device connected with the server and the opposite terminal server, and sending a switching message to the expansion controller in the storage device, wherein the management controller in the server is connected to the expansion controller through the storage control card, and the switching message is used for notifying the expansion controller to modify the established first corresponding relation between the management controller of the opposite terminal server and the managed hard disk into the second corresponding relation between the management controller of the self and the managed hard disk;
based on the second corresponding relation, the state information of the managed hard disk is obtained, and the running state of the managed hard disk is determined through the state information.
Optionally, before the interaction of the status message with the management controller of the peer server through the connected switching device, the method further includes:
after the server is electrified, interacting an election message with a management controller of an opposite-end server, wherein the election message carries election parameters;
determining the roles of the user according to the election parameters and a preset election strategy;
if the role of the expansion controller is the main management controller, sending a division request to the expansion controller according to a management instruction issued by the management device so that the expansion controller establishes a first corresponding relation between the main management controller and a managed hard disk in the storage device;
and receiving and recording the state information fed back by the managed hard disk.
Further, after the interaction of the status message with the management controller of the opposite terminal server through the connected switching device, the method further comprises:
if the state message sent by the management controller of the opposite end server is received within a preset time interval and the self role is the standby management controller, the state information of the managed hard disk managed by the management controller of the opposite end server is recorded.
With reference to the second aspect of the embodiments of the present specification, the present application provides a hard disk state synchronization device, which is applied to a management controller of a server, including:
the interaction unit is used for carrying out interaction of state messages with the management controller of the opposite terminal server through the connected exchange equipment, wherein the state messages carry state information of the managed hard disk in the storage equipment;
the system comprises a switching unit, a server and a management device, wherein the switching unit is used for sending an alarm message to the server and the management device connected with the opposite terminal server and sending a switching message to an expansion controller in a storage device if a state message sent by the management controller of the opposite terminal server is not received within a preset time interval and the state message is configured as a standby management controller, wherein the management controller in the server is connected to the expansion controller through a storage control card, and the switching message is used for informing the expansion controller to modify the established first corresponding relation between the management controller of the opposite terminal server and the managed hard disk into a second corresponding relation between the management controller of the server and the managed hard disk;
and the monitoring unit is used for acquiring the state information of the managed hard disk based on the second corresponding relation and determining the running state of the managed hard disk through the state information.
Optionally, the interaction unit is further configured to interact with an election packet with the management controller of the opposite-end server after the server is powered on, where the election packet carries election parameters;
the apparatus further comprises:
the election unit is used for determining the roles of the user according to the election parameters and a preset election strategy;
the division unit is used for sending a division request to the expansion controller according to a management instruction issued by the management device if the role of the division unit is the main management controller, so that the expansion controller establishes a first corresponding relation between the main management controller and the managed hard disk in the storage device;
and the recording unit is used for receiving and recording the state information fed back by the managed hard disk.
Further, the recording unit is further configured to, if the status message sent by the management controller of the peer server is received within a preset time interval and the own role is a standby management controller, record status information of the managed hard disk managed by the management controller of the peer server.
With reference to the third aspect of the embodiments of the present specification, the present application provides a server, including a management controller and a storage control card, where the storage control card is connected to an expansion controller in a storage device, the management controller is connected to a management controller of an opposite server through a switching device, and the server and the opposite server are connected to the management device through the switching device; a machine readable storage medium is disposed in the management controller;
the machine-readable storage medium stores machine-executable instructions executable by a management controller, the management controller being caused by the machine-executable instructions to: implementing any of the method steps described above.
With reference to the fourth aspect of the embodiments of the present specification, the present application provides a hard disk management system, including at least two servers and a storage device; the server comprises a management controller and a storage control card, the storage equipment comprises an expansion board provided with expansion controllers and a plurality of hard disks, the expansion board is respectively connected with the storage control cards of at least two servers, and the management controllers of the at least two servers are connected with the management equipment through a switching equipment;
the method comprises the steps that interaction of state messages is carried out between management controllers of at least two servers, wherein the management controllers of the at least two servers at least comprise a main management controller and a standby management controller, and the state messages carry state information of managed hard disks in storage equipment;
if the standby management controller does not receive the status message sent by the main management controller within a preset time interval, sending an alarm message to the management device and sending a switching message to the expansion controller in the storage device, wherein the switching message is used for notifying the expansion controller to modify the established first corresponding relation between the main management controller and the managed hard disk into a second corresponding relation between the standby management controller and the managed hard disk;
based on the second corresponding relation, the standby management controller acquires the state information of the managed hard disk, and determines the running state of the managed hard disk through the state information.
Optionally, after the servers are powered on, the management controllers of at least two servers interact with election messages, wherein the election messages carry election parameters;
the management controllers of the at least two servers determine roles of the management controllers according to election parameters and preset election strategies, wherein the roles comprise a main management controller and a standby management controller;
the main management controller sends a first division request to the expansion controller according to a first management instruction issued by the management equipment;
the expansion controller establishes a first corresponding relation between the main management controller and the managed hard disk in the storage device according to the first division request;
the main management controller receives and records the state information fed back by the managed hard disk.
Further, if the standby management controller receives the status message sent by the main management controller within a preset time interval, the status information of the managed hard disk managed by the main management controller is obtained and recorded.
Optionally, the storage device includes at least two servers respectively connected to the at least two storage devices;
the standby management controller sends a second division request to the expansion controller according to a second management instruction issued by the management equipment;
the expansion controller establishes a second corresponding relation between the standby management controller and the managed hard disk in the storage device different from the first division request according to the second division request;
the standby management controller receives and records the state information fed back by the managed hard disk.
The technical scheme provided by the embodiment of the specification can comprise the following beneficial effects:
in the embodiment of the present disclosure, the management controller of the server is divided into a primary management controller and a standby management controller, and manages a plurality of hard disks through the same expansion controller, and the synchronization of the state information of the managed hard disk is implemented through the interaction of the state messages between the primary management controller and the standby management controller, and in a preset time interval, if the standby management controller does not receive the state message sent by the primary management controller, the hard disk managed by the primary management controller is taken over, so that the problem that the running state of the hard disk cannot be obtained when the management controller or the storage control card fails in the case that the single management controller manages the hard disk is avoided, and the reliability of management and maintenance of the storage system is improved.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the specification and together with the description, serve to explain the principles of the specification.
FIG. 1 is a flow chart of a method for synchronizing states of a hard disk according to the present application;
fig. 2 is a block diagram of a storage system according to an embodiment of the present application;
FIG. 3 is a schematic diagram of a hard disk status synchronization device according to the present application;
FIG. 4 is a schematic diagram of a server according to the present application;
fig. 5 is a schematic diagram of another storage system according to an embodiment of the present application.
Detailed Description
Reference will now be made in detail to exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, the same numbers in different drawings refer to the same or similar elements, unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present specification.
The application provides a hard disk state synchronization method, which is applied to a management controller of a server, as shown in fig. 1, and comprises the following steps:
s100, the state message interaction is carried out with the management controller of the opposite terminal server through the connected switching equipment.
A hard disk management system, as shown in fig. 2, comprising: at least two servers and storage devices, for example, include server 1 and server 2, wherein server 2 may be referred to as the peer server of server 1. Of course, the number of servers is not limited to two, and the present embodiment will be described by taking two as an example.
The servers 1, 2 include management controllers 10, 20 and memory control cards 11, 21. The storage device 3 comprises an expansion board 30 provided with an expansion controller 300 and a number of hard disks 31n, and a plurality of ports may be provided in the expansion board 30, which are respectively connected to the storage control cards 11, 21 of at least two servers (in this case, servers 1, 2), the management controllers 10, 20 in the servers 1, 2 being connected to the expansion controller 300 via the storage control cards 11, 21, and the management controllers of the at least two servers being connected via the switching device 4 and to the management device 5. According to the structure, a plurality of servers can be connected to the expansion board of one storage device through the storage control card of the servers, so that the connection between a plurality of management controllers and the hard disk of the storage device is realized.
The management controller may be a BMC, or may be another chip for implementing component status monitoring, which is not limited herein. The memory control cards 11, 21 may be HBA (Host Bus Adapter) cards or RAID (redundant array of independent disks ) cards, or the like. The management device 5 may be a personal computer or another server, and the management device 5 may access at least two servers by means of a direct connection or a network connection.
Between the management controllers 10, 20 of the two servers 1, 2, the active management controller and the standby management controller can be performed by exchanging the option report messages. The election message may be interacted based on the switching device 4, may be a two-layer message, and carries an election parameter for election such as a MAC (media access control ) address of the management controller 10, 20, and based on the election parameter and a preconfigured election policy, for example, a management controller with a minimum or maximum MAC address is selected from the management controllers 10, 20 as a primary management controller, and other management controllers are used as standby management controllers, and the primary management controller and the standby management controller may be used as roles set by the management controllers. In the present embodiment, the management controller 10 in the server 1 may be used as a primary management controller, and the management controller 20 in the server 2 may be used as a backup management controller. Of course, it should be noted that, instead of the interaction of the selection report, the role rotation sequence of the management controller may be directly defined according to the setting of the management device 5, or other information may be interacted as an election parameter, which is not limited herein.
After the servers 1, 2 are started and the roles of the management controllers are determined based on the election or setting, monitoring of the hard disk 31n deployed in the storage device 3 may be started. In this case, the main management controller may monitor the hard disk 31n and synchronize the status information of each hard disk 31n with the standby management controller after acquiring the status information, or the main management controller and the standby management controller may monitor part of the hard disk 31n and synchronize the status information with each other.
When synchronization is performed, the management controllers 10 and 20 may send status messages to each other, where the status messages carry status information of the managed hard disk in the storage device 3. The working state of the other party can be determined by the status messages between the management controllers 10 and 20, for example, the status messages can be sent between the management controllers 10 and 20 in a period of 10ms, and if the status messages are not received in 3 periods, the management controller of the opposite end server is considered to be faulty.
S101, if the state message sent by the management controller of the opposite terminal server is not received within a preset time interval and the state message is configured as a standby management controller, sending an alarm message to the server and the management device connected with the opposite terminal server, and sending a switching message to the expansion controller in the storage device.
The time interval mentioned here may be considered as the product of the period of sending the status message and the set number of periods, for example, 3×10ms, i.e. at a time interval of 30ms, and of course, a period may be set, i.e. it is determined that the management controller fails, and the configuration is performed according to specific requirements, which is not limited herein.
In order to monitor the status of the hard disk 31n in the storage device 3, a management instruction issued by the management device 5 may be received, where the management instruction may be used to set a hard disk that needs to be managed by the management controller, and may be a hard disk identifier that carries the hard disk that needs to be managed. After receiving the management command, the master management controller 10 may generate a partition request (that is, a hard disk to be managed, which is carried in the management command) according to the management command, and send the partition request to the storage device 3. After the expansion controller 300 of the storage device 3 receives the division request, a domain (Zone) may be divided, a hard disk identifier carried in the division request is added to the divided domain, and a first correspondence relationship among the domain, the managed hard disk, and the management controller is bound. By binding, the expansion controller 300 may determine an address or an identification that can monitor the managed hard disk, so that the expansion controller 300 can send the collected state information of the managed hard disk to the management controller.
Thereafter, the expansion controller 300 may periodically transmit the detected state information of the hard disk to the main management controller 10 for recording based on the first correspondence relationship, or the main management controller 10 may periodically transmit a detection request to the expansion controller 300 so that the expansion controller 300 feeds back the state information to the main management controller 10.
In this process, the active management controller 10 may send the acquired status information to the standby management controller 20 through a status message to synchronize the recorded status information of the managed hard disk between the active management controller 10 and the standby management controller 20.
If the standby management controller 20 does not receive the status message of the active management controller 10 within the time interval, it can be considered that the active management controller 10 is malfunctioning. At this time, the standby management controller 20 may send an alarm message to the management device 5 through the switching device 4 to notify that there may be a failure of the active management controller 10 to which the management device 5 is connected. At this time, the standby management controller 20 may actively transmit a handover message to the expansion controller 300 or transmit a handover message to the expansion controller 300 based on an instruction issued by the management device 5.
The switching message is used for notifying the expansion controller to modify the established first corresponding relation between the management controller of the opposite-end server and the managed hard disk into a second corresponding relation between the management controller of the expansion controller and the managed hard disk.
Specifically, the switching message may carry information such as a hard disk identifier of the managed hard disk sent by the master management controller 10. If the standby management controller 20 determines that the primary management controller 10 fails, a handover message is sent to the expansion controller 300. After the extension controller 300 receives the handover message, it may be determined that the message is a handover message sent by the standby management controller 20 and triggered to be modified based on information such as a message type. The expansion controller 300 analyzes the hard disk identifier from the switching message, divides the managed hard disk monitored by the original and main management controller 10 into another domain, and establishes a second corresponding relationship between the domain and the standby management controller 20, so that the standby management controller 20 can monitor the state information of the managed hard disk. The message of interaction between the management controller and the storage device 3, such as the switching message and the dividing request, may be realized based on the existing protocol between the management controller and the expansion controller and the hard disk, and for the switching message, a message type field may be independently agreed in the current protocol to enable the expansion controller to determine the function of the switching message, or the message type of the dividing request may be adopted to realize, which is not limited.
S102, based on the second corresponding relation, acquiring state information of the managed hard disk, and determining the running state of the managed hard disk through the state information.
Thereafter, the standby management controller 20 may actively request the expansion controller 300 for the status information of the managed hard disk based on the second correspondence, or passively receive the status information transmitted from the expansion controller 300 to the standby management controller 20.
Note that the first correspondence and the second correspondence may be recorded in a table maintained in the expansion controller 300, for example, a domain permission table (Zone Permission Table) may be maintained in the expansion controller 300, in which information such as a domain, a managed hard disk, and a port through which the management controller accesses the expansion controller 300 may be recorded, so as to record the correspondence between the management controller and the managed hard disk.
Through the steps, the main-standby relation can be formed between the storage device 3 and the management controllers 10 and 20 of the plurality of servers 1 and 2, the fault of the main management controller 10 is determined based on the state messages interacted between the management controllers, and the switching message is sent to the expansion controller 300 connected with the main management controller 10 and the standby management controller 20, so that the expansion controller 300 performs main-standby switching, and the subsequent state information of the managed hard disk is sent to the standby management controller 20 for monitoring, thereby avoiding the problem that the managed hard disk cannot be monitored when the management controller fails for one storage device, and improving the reliability of management and maintenance of the storage system.
Optionally, before the interaction of the status message with the management controller of the peer server through the connected switching device in step S100, the method further includes:
and S103, after the server is electrified, the server interacts with the management controller of the opposite-end server to select messages.
S104, determining the roles of the user according to the election parameters and a preset election strategy.
Wherein, the election message carries election parameters. The election parameter may be, without limitation, the MAC address of the management controller, the device identification of the server, and other information that may be used for identification. The election parameter can be used for electing one active management controller from a plurality of management controllers under the condition that the election parameter can be used for sequencing.
The election policy may be to determine, based on election parameters, a management controller corresponding to a maximum value or a minimum value in the election parameters as a primary management controller, and other management controllers as standby management controllers.
And S105, if the role of the expansion controller is the primary management controller, sending a division request to the expansion controller according to a management instruction issued by the management device so that the expansion controller establishes a first corresponding relation between the primary management controller and the managed hard disk in the storage device.
S106, receiving and recording the state information fed back by the managed hard disk.
When the management controller determines that the management controller is the main management controller, a division request can be sent to the expansion controller according to a management instruction issued by the management device, and a first corresponding relation is established, so that the main management controller monitors the selected hard disk.
Further, in step S100, after the interaction of the status message with the management controller of the peer server through the connected switching device, the method further includes:
and S107, if the state message sent by the management controller of the opposite terminal server is received within a preset time interval and the self role is the standby management controller, the state information of the managed hard disk managed by the management controller of the opposite terminal server is recorded.
After the main management controller receives the state information of the managed hard disk, the state information of the managed hard disk can be obtained according to the first corresponding relation to record, and the received information such as the hard disk identification and the state information of the managed hard disk is sent to the standby management controller to synchronously record.
The application provides a hard disk state synchronization device, which is applied to a management controller of a server, as shown in fig. 3, and comprises:
the interaction unit is used for carrying out interaction of state messages with the management controller of the opposite terminal server through the connected exchange equipment, wherein the state messages carry state information of the managed hard disk in the storage equipment;
the system comprises a switching unit, a server and a management device, wherein the switching unit is used for sending an alarm message to the server and the management device connected with the opposite terminal server and sending a switching message to an expansion controller in a storage device if a state message sent by the management controller of the opposite terminal server is not received within a preset time interval and the state message is configured as a standby management controller, wherein the management controller in the server is connected to the expansion controller through a storage control card, and the switching message is used for informing the expansion controller to modify the established first corresponding relation between the management controller of the opposite terminal server and the managed hard disk into a second corresponding relation between the management controller of the server and the managed hard disk;
and the monitoring unit is used for acquiring the state information of the managed hard disk based on the second corresponding relation and determining the running state of the managed hard disk through the state information.
Optionally, the interaction unit is further configured to interact with an election packet with the management controller of the opposite-end server after the server is powered on, where the election packet carries election parameters;
the device further comprises:
the election unit is used for determining the roles of the user according to the election parameters and a preset election strategy;
the division unit is used for sending a division request to the expansion controller according to a management instruction issued by the management device if the role of the division unit is the main management controller, so that the expansion controller establishes a first corresponding relation between the main management controller and the managed hard disk in the storage device;
and the recording unit is used for receiving and recording the state information fed back by the managed hard disk.
Further, the recording unit is further configured to, if the status message sent by the management controller of the peer server is received within a preset time interval and the own role is a standby management controller, record status information of the managed hard disk managed by the management controller of the peer server.
The application provides a server, as shown in figure 4, which comprises a management controller and a storage control card, wherein the storage control card is connected with an expansion controller in storage equipment, the management controller is connected with a management controller of an opposite-end server through a switching device, and the server and the opposite-end server are connected to the management device through the switching device; a machine readable storage medium is disposed in the management controller;
the machine-readable storage medium stores machine-executable instructions executable by a management controller, the management controller being caused by the machine-executable instructions to: the method steps are realized.
The application provides a hard disk management system, as shown in figure 2, comprising at least two servers and storage equipment; the server comprises a management controller and a storage control card, the storage equipment comprises an expansion board provided with expansion controllers and a plurality of hard disks, the expansion board is respectively connected with the storage control cards of at least two servers, and the management controllers of the at least two servers are connected with the management equipment through a switching equipment;
the method comprises the steps that interaction of state messages is carried out between management controllers of at least two servers, wherein the management controllers of the at least two servers at least comprise a main management controller and a standby management controller, and the state messages carry state information of managed hard disks in storage equipment;
if the standby management controller does not receive the status message sent by the main management controller within a preset time interval, sending an alarm message to the management device and sending a switching message to the expansion controller in the storage device, wherein the switching message is used for notifying the expansion controller to modify the established first corresponding relation between the main management controller and the managed hard disk into a second corresponding relation between the standby management controller and the managed hard disk;
based on the second corresponding relation, the standby management controller acquires the state information of the managed hard disk, and determines the running state of the managed hard disk through the state information.
Optionally, after the servers are powered on, the management controllers of at least two servers interact with election messages, wherein the election messages carry election parameters;
the management controllers of the at least two servers determine roles of the management controllers according to election parameters and preset election strategies, wherein the roles comprise a main management controller and a standby management controller;
the main management controller sends a first division request to the expansion controller according to a first management instruction issued by the management equipment;
the expansion controller establishes a first corresponding relation between the main management controller and the managed hard disk in the storage device according to the first division request;
the main management controller receives and records the state information fed back by the managed hard disk.
Further, if the standby management controller receives the status message sent by the main management controller within a preset time interval, the status information of the managed hard disk managed by the main management controller is obtained and recorded.
Optionally, the standby management controller sends a second division request to the expansion controller according to a second management instruction issued by the management device;
the expansion controller establishes a second corresponding relation between the standby management controller and the managed hard disk in the storage device according to the second division request;
the standby management controller receives and records the state information fed back by the managed hard disk.
Here, in the case shown in fig. 5, the server 1 and the server 2 may be connected to the plurality of storage devices 3A, 3B, and 3C, respectively, and the worker may cause the server 1 and the server 2 to manage the hard disk in one or more of the storage devices, respectively, according to actual needs, and may take over by another server in the case of a failure of one server, and of course, the number of servers is not limited to two.
It should be noted that, at the same time, one storage device can only be managed by one server, and the primary storage device may not be distinguished, i.e., the storage device managed by one server is configured, then the management controller in this server may be regarded as the primary management controller, and the other server may be regarded as the standby management controller. The opposite configuration may be made for another storage device, for example, the management controller 10 of the server 1 monitors the hard disk of the storage device 3A, and the management controller 20 of the server 2 monitors the hard disk of the storage devices 3B, 3C. It should be noted that, because the storage devices corresponding to the servers are different, there is no case that the active management controller works and the standby management controller stands by, because the storage devices corresponding to the active management controller and the standby management controller are different, the active management controller and the standby management controller need to be in a working state respectively in the same time period, and the state information corresponding to the different storage devices, that is, the management controller 10 of the server 1 needs to send the state information corresponding to the hard disk of the storage device 3A to the management controller 20 of the server 2, and the management controller 20 of the server 2 sends the state information corresponding to the hard disk of the storage device 3B and 3C to the management controller 10 of the server 1.
Then, it is assumed that, when the management controller 10 of the server 1 fails, the management controller 20 of the server 2 may take over the hard disk managed by the storage device 3A, so as to achieve synchronization for different storage devices among different servers in the storage system.
The technical scheme provided by the embodiment of the specification can comprise the following beneficial effects:
in the embodiment of the present disclosure, the management controller of the server is divided into a primary management controller and a standby management controller, and manages a plurality of hard disks through the same expansion controller, and the synchronization of the state information of the managed hard disk is implemented through the interaction of the state messages between the primary management controller and the standby management controller, and in a preset time interval, if the standby management controller does not receive the state message sent by the primary management controller, the hard disk managed by the primary management controller is taken over, so that the problem that the running state of the hard disk cannot be obtained when the management controller or the storage control card fails in the case that the single management controller manages the hard disk is avoided, and the reliability of management and maintenance of the storage system is improved.
It is to be understood that the present description is not limited to the precise arrangements and instrumentalities shown in the drawings, which have been described above, and that various modifications and changes may be made without departing from the scope thereof.
The foregoing description of the preferred embodiments is provided for the purpose of illustration only, and is not intended to limit the scope of the disclosure, since any modifications, equivalents, improvements, etc. that fall within the spirit and principles of the disclosure are intended to be included within the scope of the disclosure.
Claims (11)
1. A hard disk state synchronization method is characterized by being applied to a management controller of a server and comprising the following steps:
through the connected exchange equipment, the exchange equipment interacts with a management controller of an opposite terminal server, wherein the state message carries state information of a managed hard disk in the storage equipment;
if the state message sent by the management controller of the opposite terminal server is not received within a preset time interval and the state message is configured as a standby management controller, sending an alarm message to the server and the management device connected with the opposite terminal server, and sending a switching message to the expansion controller in the storage device, wherein the management controller in the server is connected to the expansion controller through the storage control card, and the switching message is used for notifying the expansion controller to modify the first corresponding relation between the established management controller of the opposite terminal server and the managed hard disk into the second corresponding relation between the management controller of the opposite terminal server and the managed hard disk;
and acquiring state information of the managed hard disk based on the second corresponding relation, and determining the running state of the managed hard disk according to the state information.
2. The method of claim 1, further comprising, prior to the interaction of the status message with the management controller of the peer server via the connected switching device:
after the server is electrified, interacting an election message with a management controller of an opposite-end server, wherein the election message carries election parameters;
determining the roles of the user according to the election parameters and a preset election strategy;
if the role of the expansion controller is the main management controller, sending a division request to the expansion controller according to a management instruction issued by the management device so that the expansion controller establishes a first corresponding relation between the main management controller and a managed hard disk in the storage device;
and receiving and recording the state information fed back by the managed hard disk.
3. The method of claim 2, further comprising, after the interaction of the status message with the management controller of the peer server via the connected switching device:
if the state message sent by the management controller of the opposite end server is received within a preset time interval and the self role is the standby management controller, the state information of the managed hard disk managed by the management controller of the opposite end server is recorded.
4. A hard disk state synchronization device, characterized by being applied to a management controller of a server, comprising:
the interaction unit is used for carrying out interaction of state messages with the management controller of the opposite terminal server through the connected exchange equipment, wherein the state messages carry state information of the managed hard disk in the storage equipment;
the system comprises a switching unit, a storage device and a management controller, wherein the switching unit is used for sending an alarm message to the server and a management device connected with the opposite end server and sending a switching message to the expansion controller in the storage device if a state message sent by the management controller of the opposite end server is not received within a preset time interval and the state message is configured as a standby management controller, wherein the management controller in the server is connected to the expansion controller through the storage control card, and the switching message is used for informing the expansion controller to modify a first corresponding relation between the established management controller of the opposite end server and the managed hard disk into a second corresponding relation between the management controller of the server and the managed hard disk;
and the monitoring unit is used for acquiring the state information of the managed hard disk based on the second corresponding relation and determining the running state of the managed hard disk through the state information.
5. The apparatus of claim 4, wherein the device comprises a plurality of sensors,
the interaction unit is further used for interacting an election message with the management controller of the opposite-end server after the server is electrified, wherein the election message carries election parameters;
the device further comprises:
the election unit is used for determining the role of the user according to the election parameters and a preset election strategy;
the division unit is used for sending a division request to the expansion controller according to a management instruction issued by the management device if the role of the division unit is a main management controller, so that the expansion controller establishes a first corresponding relation between the main management controller and a managed hard disk in the storage device;
and the recording unit is used for receiving and recording the state information fed back by the managed hard disk.
6. The apparatus according to claim 5, wherein the recording unit is further configured to, if the status message sent by the management controller of the peer server is received within a preset time interval and the role of the status message is a standby management controller, record status information of the managed hard disk managed by the management controller of the peer server.
7. The server is characterized by comprising a management controller and a storage control card, wherein the storage control card is connected with an expansion controller in storage equipment, the management controller is connected with a management controller of an opposite-end server through a switching equipment, and the server and the opposite-end server are connected to the management equipment through the switching equipment; the management controller is provided with a machine-readable storage medium;
the machine-readable storage medium stores machine-executable instructions executable by the management controller, the management controller being caused by the machine-executable instructions to: a method step of any one of claims 1-3 is achieved.
8. A hard disk management system is characterized by comprising at least two servers and storage equipment; the server comprises a management controller and a storage control card, the storage equipment comprises an expansion board provided with an expansion controller and a plurality of hard disks, the expansion board is respectively connected with the storage control cards of the at least two servers, and the management controllers of the at least two servers are connected with the management equipment through a switching equipment;
the method comprises the steps that interaction of state messages is conducted among management controllers of at least two servers, wherein the management controllers of the at least two servers at least comprise a main management controller and a standby management controller, and the state messages carry state information of managed hard disks in storage equipment;
if the standby management controller does not receive the status message sent by the main management controller within a preset time interval, sending an alarm message to the management device and sending a switching message to an expansion controller in a storage device, wherein the switching message is used for notifying the expansion controller to modify the established first corresponding relation between the main management controller and the managed hard disk into a second corresponding relation between the standby management controller and the managed hard disk;
based on the second corresponding relation, the standby management controller obtains the state information of the managed hard disk, and determines the running state of the managed hard disk according to the state information.
9. The system of claim 8, wherein the system further comprises a controller configured to control the controller,
after the servers are electrified, the management controllers of at least two servers interact with election messages, wherein the election messages carry election parameters;
the management controllers of the at least two servers determine roles of the management controllers according to the election parameters and a preset election strategy, wherein the roles comprise a main management controller and a standby management controller;
the main management controller sends a first division request to the expansion controller according to a first management instruction issued by the management equipment;
the expansion controller establishes a first corresponding relation between the main management controller and the managed hard disk in the storage device according to the first division request;
and the main management controller receives and records the state information fed back by the managed hard disk.
10. The system of claim 9, wherein the system further comprises a controller configured to control the controller,
and if the standby management controller receives the state message sent by the main management controller within a preset time interval, acquiring and recording the state information of the managed hard disk managed by the main management controller.
11. The system of claim 9, wherein the storage device comprises at least two servers respectively connected to the at least two storage devices;
the standby management controller sends a second division request to the expansion controller according to a second management instruction issued by the management equipment;
the expansion controller establishes a second corresponding relation between the standby management controller and the managed hard disk in the storage device different from the first partition request according to the second partition request;
and the standby management controller receives and records the state information fed back by the managed hard disk.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110710336.7A CN113448802B (en) | 2021-06-25 | 2021-06-25 | Method, device, system and server for synchronizing states of hard disks |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110710336.7A CN113448802B (en) | 2021-06-25 | 2021-06-25 | Method, device, system and server for synchronizing states of hard disks |
Publications (2)
Publication Number | Publication Date |
---|---|
CN113448802A CN113448802A (en) | 2021-09-28 |
CN113448802B true CN113448802B (en) | 2023-11-07 |
Family
ID=77812764
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110710336.7A Active CN113448802B (en) | 2021-06-25 | 2021-06-25 | Method, device, system and server for synchronizing states of hard disks |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113448802B (en) |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107766203A (en) * | 2017-10-10 | 2018-03-06 | 郑州云海信息技术有限公司 | A kind of method of hard disk failure in fast positioning SDS |
CN107819708A (en) * | 2016-09-12 | 2018-03-20 | 阿里巴巴集团控股有限公司 | Data processing method, system and equipment based on virtual machine (vm) migration |
CN110109790A (en) * | 2019-05-13 | 2019-08-09 | 深圳前海微众银行股份有限公司 | Server hard disc management method, device, equipment and computer readable storage medium |
CN112014669A (en) * | 2020-08-25 | 2020-12-01 | 武汉中元华电电力设备有限公司 | Online detection method and system for angle difference and ratio difference of merging unit |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108874719B (en) * | 2017-05-16 | 2020-10-20 | 杭州海康威视数字技术股份有限公司 | PCIe bus-based expansion storage device |
-
2021
- 2021-06-25 CN CN202110710336.7A patent/CN113448802B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107819708A (en) * | 2016-09-12 | 2018-03-20 | 阿里巴巴集团控股有限公司 | Data processing method, system and equipment based on virtual machine (vm) migration |
CN107766203A (en) * | 2017-10-10 | 2018-03-06 | 郑州云海信息技术有限公司 | A kind of method of hard disk failure in fast positioning SDS |
CN110109790A (en) * | 2019-05-13 | 2019-08-09 | 深圳前海微众银行股份有限公司 | Server hard disc management method, device, equipment and computer readable storage medium |
CN112014669A (en) * | 2020-08-25 | 2020-12-01 | 武汉中元华电电力设备有限公司 | Online detection method and system for angle difference and ratio difference of merging unit |
Non-Patent Citations (1)
Title |
---|
实时数据库***双机热备机制设计与实现;杨晓芬;王永会;刘轶;;计算机工程与应用(第29期);全文 * |
Also Published As
Publication number | Publication date |
---|---|
CN113448802A (en) | 2021-09-28 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US9916113B2 (en) | System and method for mirroring data | |
CN103546914B (en) | A kind of method and device of the active and standby management of HSS | |
JP3706179B2 (en) | Communication controller between dual magnetic disk controllers | |
US20070220301A1 (en) | Remote access control management module | |
JPH04502542A (en) | Distributed switching architecture for communication module redundancy | |
CN101594383B (en) | Method for monitoring service and status of controllers of double-controller storage system | |
US8782462B2 (en) | Rack system | |
CN102025790B (en) | Address allocation method, device and system | |
CN110677282B (en) | Hot backup method of distributed system and distributed system | |
WO2008014639A1 (en) | A distributed master and standby managing method and system based on the network element | |
CN102394914A (en) | Cluster brain-split processing method and device | |
CN106850255A (en) | A kind of implementation method of multi-computer back-up | |
US20230198874A1 (en) | Link detection method and system | |
JPH03164837A (en) | Spare switching system for communication control processor | |
WO2008035334A2 (en) | Fault-tolerant medium access control (mac) address assignment in network elements | |
CN113448802B (en) | Method, device, system and server for synchronizing states of hard disks | |
CN114760224A (en) | System, method, apparatus, and storage medium for monitoring status of network channels | |
EP1497731B1 (en) | A method and a system for ensuring a bus and a control server | |
KR101694298B1 (en) | Apparatus for electing a master in redundancy system | |
JP3555047B2 (en) | Compound computer system | |
CN114124803B (en) | Device management method and device, electronic device and storage medium | |
CN106776152B (en) | Data backup method and device | |
CN116346582A (en) | Method, device, equipment and storage medium for realizing redundancy of main network and standby network | |
CN113742142B (en) | Method for managing SATA hard disk by storage system and storage system | |
CN112732482A (en) | Cifs service backup switching method, device, equipment and readable storage medium |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |