CN117472289B

CN117472289B - Storage configuration adjustment method, device, system, equipment and medium of server

Info

Publication number: CN117472289B
Application number: CN202311815037.5A
Authority: CN
Inventors: 魏文星
Original assignee: Suzhou Metabrain Intelligent Technology Co Ltd
Current assignee: Suzhou Metabrain Intelligent Technology Co Ltd
Priority date: 2023-12-27
Filing date: 2023-12-27
Publication date: 2024-03-15
Anticipated expiration: 2043-12-27
Also published as: CN117472289A

Abstract

The invention discloses a method, a device, a system, equipment and a medium for adjusting storage configuration of a server, which are applied to the technical field of servers. Determining a current hard disk topology mapping relation according to current hard disk state information of a server, a cable connection relation and initial routing information of the last moment; when the storage configuration requirement of the server is determined to change according to the current hard disk topology mapping relation and the initial hard disk topology mapping relation at the previous moment, optimizing the current hard disk topology mapping relation to obtain an optimized hard disk topology mapping relation; and determining optimized route information according to the optimized hard disk topology mapping relation, and adjusting the connection relation of the uplink port and the downlink port by a link switch in the hard disk backboard according to the optimized route information. The invention can solve the problems of low efficiency and complexity in the storage configuration adjustment process of the related technology, can simply and efficiently adjust the storage configuration of the server, and ensures that the storage performance of a user reaches the optimum.

Description

Storage configuration adjustment method, device, system, equipment and medium of server

Technical Field

The present invention relates to the field of server technologies, and in particular, to a method, an apparatus, a system, an electronic device, and a readable storage medium for adjusting storage configuration of a server.

Background

Along with the rapid development of cloud computing and big data technology, more and more electronic data are generated in daily life, and the demand for storage servers is also increasing, especially the demand for high-performance storage servers represented by solid state disks.

Because of the different storage requirements of different users, the storage configuration of the server needs to be adapted. In order to meet the storage configuration requirement of a user, the related technology adjusts the topological structure of the hard disk by adjusting the position of the hard disk, and then the topological structure of the hard disk is matched with the hard disk configuration required by the user. However, the related art needs to insert the hard disk on the corresponding hard disk slot of the front panel of the server chassis according to different hard disk topologies, and additional manual workload is required to be added, which is not only inefficient, but also increases the complexity of production and operation and maintenance.

In view of this, simply and efficiently implementing the adjustment of the storage configuration of the server on the basis of ensuring that the storage performance of the user reaches the optimum is a technical problem that needs to be solved by those skilled in the art.

Disclosure of Invention

The invention provides a storage configuration adjustment method, a device, a system, electronic equipment and a readable storage medium of a server, which can simply and efficiently adjust the storage configuration of the server and ensure that the storage performance of a user reaches the optimal.

In order to solve the technical problems, the invention provides the following technical scheme:

in one aspect, the present invention provides a method for adjusting storage configuration of a server, which is applied to a baseboard management controller, wherein a process of adjusting storage configuration of the server by the baseboard management controller includes:

determining a current hard disk topology mapping relation according to current hard disk state information of a server, a cable connection relation and initial routing information of the last moment; each hard disk of the server is connected with a bus port of a central processing unit of the main board through a link switch positioned on a hard disk backboard;

when the storage configuration requirement of the server is determined to change according to the current hard disk topology mapping relation and the initial hard disk topology mapping relation at the last moment, optimizing the current hard disk topology mapping relation to obtain an optimized hard disk topology mapping relation;

determining optimized route information according to the optimized hard disk topology mapping relation, so that the link switch adjusts the connection relation between an uplink port and a downlink port according to the optimized route information;

The cable connection relation represents a cable connection mode between the hard disk backboard and the central processing unit; the hard disk topology mapping relation represents the mounting corresponding relation between each hard disk of the server and each central processing unit; the route information is used for representing the connection relation between the uplink port and the downlink port in the link switch.

In a first exemplary embodiment, the determining the current hard disk topology mapping relationship according to the current hard disk state information of the server, the cable connection relationship, and the initial routing information of the last moment includes:

determining at least one hard disk to be demanded in an in-place state according to the current hard disk state information of the server;

determining an initial connection relation between an uplink port and a downlink port of the link switch according to the initial routing information at the previous moment;

determining an uplink connection relation between an uplink port of the link switch and a bus port of a central processing unit of the main board and a downlink connection relation between a downlink port of the link switch and each hard disk according to the cable connection relation;

and determining the mounting corresponding relation between each hard disk to be required and the bus port of the central processing unit according to each uplink connection relation and each downlink connection relation so as to obtain the current hard disk topology mapping relation.

In a second exemplary embodiment, the determining the current hard disk topology mapping relationship according to the current hard disk state information of the server, the cable connection relationship, and the initial routing information of the last moment includes:

constructing a hard disk topology remapping function configuration option in a user management interface of a baseboard management controller in advance; the hard disk topology remapping function configuration options comprise an opening option and a closing option;

when a hard disk topology remapping function starting instruction is received, determining a current hard disk topology mapping relation according to current hard disk state information of a server, a cable connection relation and initial routing information of the last moment.

In a third exemplary embodiment, before determining the uplink connection relationship between the uplink port of the link switch and the bus port of the central processor of the motherboard according to the cable connection relationship, the method further includes:

constructing a cable configuration area in a user management interface of a baseboard management controller in advance; the cable configuration area includes a cable connection relationship upload option;

when a cable connection relation uploading instruction is received, the cable connection relation corresponding to the hard disk backboard is obtained through analyzing the cable connection relation uploading instruction, and the cable connection relation is stored under a preset path.

In a fourth exemplary embodiment, after the user management interface of the baseboard management controller constructs the cable configuration area, the method further includes:

constructing a cable connection relation adjustment option in a cable configuration area in a user management interface of a baseboard management controller in advance;

when a cable connection relation adjustment instruction is received, obtaining a new cable connection relation corresponding to the hard disk backboard by analyzing the cable connection relation adjustment instruction;

and updating the current cable connection relation under the preset path according to the new cable connection relation.

In a fifth exemplary embodiment, the optimizing the current hard disk topology mapping relationship to obtain an optimized hard disk topology mapping relationship includes:

determining a target mounting corresponding relation meeting a pre-built storage configuration performance tuning principle according to the current storage configuration information of the server and the hard disk configuration condition of the main board;

and taking the target mounting corresponding relation as an optimized hard disk topology mapping relation.

In a sixth exemplary embodiment, the determining, according to the current storage configuration information of the server and the hard disk configuration condition of the motherboard, the target mount correspondence that meets the pre-built storage configuration performance tuning rule includes:

Generating a storage configuration performance tuning principle according to the fact that the number of the mounted hard disks of each central processing unit is the same and the number of the mounted hard disks of each bus port of the same central processing unit is the same;

and determining a target mounting corresponding relation according to the current storage configuration information of the server and the hard disk configuration condition of the main board based on the storage configuration performance tuning principle.

In a seventh exemplary embodiment, the determining, according to the current storage configuration information of the server and the hard disk configuration condition of the motherboard, the target mount correspondence that meets the pre-built storage configuration performance tuning rule includes:

determining the total number of hard disk demands of a current server and the current mounting corresponding relation of each hard disk to be demanded according to the current hard disk topology mapping relation, and taking the total number of hard disk demands of the current server and the current mounting corresponding relation of each hard disk to be demanded as the current storage configuration information;

the number of the central processing units contained in the main board, the number of bus ports of each central processing unit and the port bandwidth are obtained to be used as the hard disk configuration condition;

based on the fact that the number of the mounted hard disks of each central processing unit is the same and the number of the mounted hard disks of different bus ports of the same central processing unit is the same, the hard disks to be adjusted for topological relation adjustment and the target bus ports of the mounted target central processing units of the hard disks to be adjusted are determined from the hard disks to be required.

In an eighth exemplary embodiment, the determining the optimized routing information according to the optimized hard disk topology mapping relationship includes:

determining an initial uplink port and an initial downlink port of the hard disk to be adjusted according to the initial routing information;

determining a target uplink port corresponding to a target bus port of the target central processing unit according to the cable connection relation;

taking the initial downlink port and the target uplink port as current route information of the hard disk to be adjusted;

and generating optimized route information according to the current route information of each hard disk to be adjusted.

In a ninth exemplary embodiment, further comprising:

pre-constructing a table database; the table database comprises an initial routing table, an initial hard disk topology mapping table, a detection topology mapping table, an optimization topology mapping table and an optimization routing table; the initial routing table is used for storing initial routing information at the previous moment; the initial hard disk topology mapping table is used for storing the initial hard disk topology mapping relation at the last moment;

updating the detection topology mapping table according to the current hard disk topology mapping relation;

updating the optimized topology mapping table according to the optimized hard disk topology mapping relation;

And updating the optimized routing table according to the optimized routing information.

In a tenth exemplary embodiment, after updating the optimized routing table according to the optimized routing information, the method further includes:

and after detecting that the link switch adjusts the connection relation between the uplink port and the downlink port according to the optimized route information, updating the initial route table according to the optimized route table, and updating the initial hard disk topology mapping table according to the optimized topology mapping table.

In an eleventh exemplary embodiment, the determining that the storage configuration requirement of the server changes according to the current hard disk topology mapping relationship and the initial hard disk topology mapping relationship at the previous time further includes:

determining a hard disk to be demanded at the current moment according to the current hard disk topology mapping relation;

determining an initial hard disk to be demanded at the last moment according to the initial hard disk topology mapping relation;

and if the hard disk to be required at the current moment is different from the initial hard disk to be required, the storage configuration requirement of the server is changed.

Another aspect of the present invention provides a storage configuration adjustment device of a server, applied to a baseboard management controller, including:

The hard disk topology detection module is used for determining a current hard disk topology mapping relation according to current hard disk state information of the server, the cable connection relation and initial routing information of the last moment; each hard disk of the server is connected with a bus port of a central processing unit of the main board through a link switch positioned on a hard disk backboard;

the storage demand change determining module is used for optimizing the current hard disk topology mapping relation to obtain an optimized hard disk topology mapping relation when determining that the storage configuration demand of the server changes according to the current hard disk topology mapping relation and the initial hard disk topology mapping relation at the last moment; the hard disk topology mapping relation represents the mounting corresponding relation between each hard disk of the server and each central processing unit;

the hard disk topology optimization module is used for determining optimized route information according to the optimized hard disk topology mapping relation so that the link switch can adjust the connection relation between the uplink port and the downlink port according to the optimized route information; the route information is used for representing the connection relation between the uplink port and the downlink port in the link switch.

The invention also provides an electronic device comprising a processor for implementing the steps of the method for adjusting the storage configuration of a server according to any one of the preceding claims when executing a computer program stored in a memory.

The present invention also provides a readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps of the storage configuration adjustment method of a server as described in any of the preceding claims.

The invention finally provides a storage configuration adjustment system of the server, which comprises a hard disk state monitoring subsystem, a routing subsystem and a baseboard management controller;

the hard disk state monitoring subsystem and the routing subsystem are arranged on a hard disk backboard of a server, and the baseboard management controller is arranged on a main board of the server;

the hard disk state monitoring subsystem is used for sending the current hard disk state information of the server to the baseboard management controller; the baseboard management controller is used for adjusting the storage configuration of the server; the routing subsystem comprises a link switch, and is used for sending the initial routing information at the previous moment to the baseboard management controller, and adjusting the connection relation between the uplink port and the downlink port according to the optimized routing information sent by the baseboard management controller.

In a first exemplary embodiment, the hard disk state monitoring subsystem includes a hard disk presence detector, a state register, a protocol converter, and a sideband signal connector;

one end of the hard disk in-place detector is connected in a first type connector in a hard disk slot of the hard disk backboard, and the other end of the hard disk in-place detector is connected with the status register; one end of the protocol converter is connected with one end of the state register, the other end of the protocol converter is connected with the sideband signal connector, and the sideband signal connector is connected with the baseboard management controller through a target bus;

the hard disk in-place detector is used for determining whether the corresponding hard disk is in place according to the level signals of pins connected with the first type of connectors; the state register is used for generating current hard disk state information according to the current in-place state of each hard disk of the server; the protocol converter is used for converting the current hard disk state information into data conforming to a target bus protocol and transmitting the data through the sideband signal connector.

In a second exemplary embodiment, the total number of the hard disk in-place detectors is the same as the total number of the hard disk slots of the hard disk backboard, and corresponds to one;

The first level sampling pin of the hard disk in-place detector is connected with the hard disk in-place pin of the first type connector in the corresponding hard disk slot; the second level sampling pin of the hard disk in-place detector is connected with the hard disk type identification pin of the first type connector in the corresponding hard disk slot;

the hard disk in-place detector is used for determining whether the corresponding hard disk is in place or not according to the level signals of the first level sampling pin and the second level sampling pin based on the type of the hard disk inserted by the corresponding hard disk slot.

In a third exemplary embodiment, the hard disk bit detector is a complex programmable logic device; the state register comprises a plurality of registers, and each register corresponds to one hard disk of the server;

when the complex programmable logic device detects that the first hard disk is in place, writing in-place identification information into a first register corresponding to the first hard disk; and when the second hard disk is detected to be out of place, writing the out-of-place identification information into a first register corresponding to the second hard disk.

In a fourth exemplary embodiment, the sideband signal connector is connected to the baseboard management controller via an integrated circuit bus;

The protocol converter encapsulates an input/output extended data transmission protocol, and is used for converting the current hard disk state information into bus data corresponding to the integrated circuit bus and sending the bus data to the baseboard management controller.

In a fifth exemplary embodiment, each hard disk of the server is mounted on a high-speed serial computer expansion bus standard bus port of a central processing unit; the link switch is a high-speed serial computer expansion bus standard switch;

and each downlink port of the high-speed serial computer expansion bus standard switch is respectively connected with a first connector in each hard disk slot of the hard disk backboard, and each uplink port is respectively connected with the high-speed serial computer expansion bus standard bus port through each uplink interface positioned on the hard disk backboard.

In a sixth exemplary embodiment, the high speed serial computer expansion bus standard switch is connected to the sideband signal connector via an integrated circuit bus;

the high-speed serial computer expansion bus standard switch transmits the initial routing information to the baseboard management controller through the sideband signal connector through the integrated circuit bus, and the baseboard management controller transmits the optimized routing information to the high-speed serial computer expansion bus standard switch through the sideband signal connector.

The technical scheme provided by the invention has the advantages that whether the storage configuration requirement of the user of the server is changed or not is automatically determined by monitoring the hard disk change information of the server, after the storage configuration requirement of the server is changed, the optimal hard disk topology meeting the storage configuration requirement of the user is determined according to the storage configuration requirement of the user and the hard disk topology mapping relation, the optimized route information is determined according to the optimal hard disk topology mapping relation, and the link switch automatically adjusts the newly configured topology of the hard disk to the optimal topology according to the optimized route information, so that the connection between the bus port of the central processing unit and the hard disk is automatically adjusted according to the current quantity of the hard disks installed on the server, the hard disk topology is optimized, the storage configuration of the server can be simply and efficiently adjusted, and the storage performance of the user is ensured to be optimal.

In addition, the invention also provides a corresponding implementation device, a corresponding system, a corresponding electronic device and a corresponding readable storage medium for the storage configuration adjustment method of the server, so that the method has more practicability, and the device, the system, the electronic device and the corresponding readable storage medium have corresponding advantages.

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 invention as claimed.

Drawings

For a clearer description of the present invention or of the technical solutions related thereto, the following brief description will be given of the drawings used in the description of the embodiments or of the related art, it being obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings may be obtained from these drawings without the inventive effort of a person skilled in the art.

Fig. 1 is a schematic diagram of a hardware structure of a server in an exemplary scenario provided by the present invention;

FIG. 2 is a schematic diagram of a topology of a server in an exemplary scenario provided by the present invention;

FIG. 3 is a schematic diagram illustrating a topology adjustment of a server according to a related art;

FIG. 4 is a schematic diagram illustrating a topology adjustment of a server according to another related art provided by the present invention;

FIG. 5 is a schematic diagram illustrating a topology adjustment of a server according to another related art provided by the present invention;

FIG. 6 is a flowchart illustrating another method for adjusting storage configuration of a server according to the present invention;

FIG. 7 is a block diagram of an embodiment of a storage configuration adjustment apparatus for a server according to the present invention;

FIG. 8 is a block diagram of an embodiment of an electronic device according to the present invention;

FIG. 9 is a block diagram of a specific embodiment of a storage configuration adjustment system for a server according to the present invention;

FIG. 10 is a block diagram of another embodiment of a storage configuration adjustment system for a server according to the present invention;

FIG. 11 is a block diagram of a specific embodiment of a hard disk status monitoring subsystem provided by the present invention;

fig. 12 is a block diagram of another embodiment of a storage configuration adjustment system of a server according to the present invention.

Detailed Description

In order to make the technical scheme of the present invention better understood by those skilled in the art, the present invention will be further described in detail with reference to the accompanying drawings and the detailed description. Wherein the terms "first," "second," "third," "fourth," and the like in the description and in the claims and in the above-described figures, are used for distinguishing between different objects and not for describing a particular sequential order. Furthermore, the terms "comprise" and "have," as well as any variations of the two, are intended to cover a non-exclusive inclusion. The term "exemplary" means "serving as an example, embodiment, or illustration. Any embodiment described herein as "exemplary" is not necessarily to be construed as preferred or advantageous over other embodiments.

At present, a high-performance storage server represented by a solid state disk is widely used for storing electronic data generated by daily work and life, wherein compared with traditional mechanical hard disks such as an SAS (Serial Attached Small Computer System Interface, serial connection small computer system interface) and a serial hard disk, a solid state disk based on a pci (peripheral component interconnect express, high-speed serial computer expansion bus standard) bus is directly connected to a pci bus of a CPU (Central Processing Unit ), the storage performance is better, and the solid state disk is widely applied to the high-performance storage server, such as an Nvme (Non Volatile Memory Host Controller Interface Specification ) hard disk.

After the size and structural components of the server are determined, the positions of the hard disks and the maximum number of the hard disks which can be assembled by the server are determined, and the corresponding hard disk connection relationship, namely the hard disk topological structure, is determined. Different users have different storage configuration requirements on the server, which may occur when the server modifies the storage configuration. For example, the original 12 hard disks of the server, the user a needs 10 hard disks, the user B needs 6 hard disks, and in order to meet the optimal storage configuration of the user, different hard disk topologies are set according to the configuration requirements of the user, and the manner of "a requirement corresponds to a topology" causes the design, production and operation of the server to be complicated. When the storage configuration requirement of the user on the server is different from the original storage configuration of the server, in order to achieve the optimal storage performance of the user, the hard disk of the server needs to be adjusted, and the corresponding hard disk topological structure needs to be modified according to different hard disk configuration requirements. One related technology is to change the topology of the hard disk by manually modifying a cable between the Pcie interface of the CPU connected with the main board and the hard disk back plate, namely, manually adjusting the connection relation between the hard disk and the Pcie interface of the CPU according to the condition of the inserted hard disk on the hard disk back plate. This approach not only requires additional cable fabrication, but also increases cost and accuracy by manual adaptation. Another related technology realizes the change of the topological structure of the hard disk by adjusting the position of the hard disk, and the mode keeps a cable between a Pcie interface of a main board CPU and a hard disk backboard motionless, adjusts the position of the hard disk on the hard disk backboard, and enables the hard disk to be connected with the corresponding Pcie interface to form optimal topological connection. However, the method needs to insert the hard disk on different hard disk slots of the front panel of the chassis according to different hardware topologies, which increases the complexity of production and operation and maintenance. In another related technology, when the configuration requirement of a user hard disk is modified, the optimal topology is abandoned, the current topology is kept unchanged, namely, the hard disk topology structure is not adjusted, and the performance of the hard disk in certain scenes can be influenced.

For example, as shown in fig. 1, the current server motherboard includes 12 hard disks and two CPUs, the hard disks may be represented as hard disk 1, hard disk 2, … …, hard disk 12, and the two CPUs, namely CPU0 and CPU1, each hard disk is connected to the pci bus of the CPU by a cable, and CPU0 and CPU1 are connected to each other by a UPI (Ultra Path Interconnect, hyper path interconnect) bus. As shown in fig. 2, CPU0 is connected to hard disk 1, hard disk 2, … …, and hard disk 6 via cables, and CPU1 is connected to hard disk 7, hard disk 8, … …, and hard disk 12 via cables. The storage configuration of the user is required to be 6 hard disks, and one related technology is as shown in fig. 3, after removing the hard disks 7 to 12 connected to the CPUI, the manner of connecting the cables between the scie interface of the main board CPU1 and the back boards of the hard disks 4, 5 and 6 is manually modified. Another related art is shown in fig. 4, which adjusts the hard disk 4, the hard disk 5, the hard disk 6 connected to the CPU o to the slot of the CPU 1. While another related art is shown in fig. 5, only the hard disk 7 to the hard disk 12 connected to the CPU1 are removed, and no adjustment is made to the hard disk topology. Therefore, in order to achieve the optimal storage performance of the user, the related technology needs extra materials and workload in the process of adjusting the storage configuration of the server, and the design, production and operation and maintenance difficulties are increased.

In view of this, the invention automatically determines whether the storage configuration requirement of the user of the server changes by monitoring the hard disk change information of the server, and after the storage configuration requirement of the server changes, determines the optimal hard disk topology meeting the storage configuration requirement of the user according to the storage configuration requirement of the user and the hard disk topology mapping relation, determines the optimized route information according to the optimal hard disk topology mapping relation, and the link switch automatically adjusts the newly configured topology of the hard disk to the optimal topology according to the optimized route information, thereby simply and efficiently adjusting the storage configuration of the server and ensuring that the storage performance of the user reaches the optimal. Having described aspects of the invention, various non-limiting embodiments of the invention are described in detail below. Numerous specific details are set forth in the following description in order to provide a better understanding of the invention. It will be understood by those skilled in the art that the present invention may be practiced without these specific details. In other instances, well known methods, procedures, components, and circuits have not been described in detail so as not to obscure the present invention.

Referring to fig. 6, fig. 6 is a flow chart of a method for adjusting storage configuration of a server according to the present embodiment, which is applied to a baseboard management controller, that is, a BMC, and the process of the baseboard management controller to adjust the storage configuration of the server may include the following steps:

s601: and determining the current hard disk topology mapping relation according to the current hard disk state information of the server, the cable connection relation and the initial routing information of the last moment.

In this embodiment, the motherboard of the server includes a plurality of CPUs, each CPU is connected to a cable of each hard disk on a hard disk back plate of the server through a target bus such as a pci bus, the hard disk back plate includes a link switch, and each hard disk of the server is connected to a bus port of a target bus of a central processor of the motherboard through the link switch located on the hard disk back plate. The current hard disk state information is an in-place state of a hard disk of the current hard disk backboard, and may include hard disk information contained in the hard disk backboard at the current moment, where the hard disk information may include the number and the position state of the hard disks, in other words, the current hard disk state information is used for reflecting which hard disk slots of the hard disk backboard are used for installing the hard disk and which hard disk slots are empty. The cable connection relationship indicates a cable connection manner between the hard disk back plate and the central processing unit, that is, a connection relationship between an uplink interface of the hard disk back plate and a bus port of each CPU, in other words, which uplink interface is connected to which bus port of which CPU. The routing information indicates a connection relationship between an uplink port and a downlink port in the link switch, and correspondingly, the initial routing information indicates a connection relationship between an uplink port and a downlink port in the link switch at a time immediately before the current obtaining time of the hard disk state information, which may include a connection relationship between an uplink port and a downlink port in the link switch, an uplink port of the link switch corresponds to an uplink interface of a hard disk backboard connected with the uplink port, and a downlink port of the link switch corresponds to a connector of a hard disk slot connected with the downlink port of the link switch, that is, a connection relationship between how the uplink port and the downlink port of the link switch are connected, and a connection relationship between the uplink port and the downlink port of the hard disk backboard. The hard disk topology mapping relation represents the mounting corresponding relation between each hard disk of the server and each central processing unit; the current hard disk topology mapping relationship refers to a mounting relationship between a hard disk and a central processing unit at the time of acquiring the current hard disk state information, namely, which bus port of which CPU is mounted with the hard disk of which hard disk slot position. When the connection relation between the uplink port and the downlink port of the link switch and the uplink port and the downlink port of the hard disk backboard is clear, the connection relation between the uplink port of the hard disk backboard and the bus port of each CPU can be determined, and then the hard disk of which hard disk slot is mounted on which bus port of which CPU is determined, namely the current hard disk topology mapping relation is determined.

S602: when the storage configuration requirement of the server is determined to change according to the current hard disk topology mapping relation and the initial hard disk topology mapping relation at the last moment, the current hard disk topology mapping relation is optimized, and the optimized hard disk topology mapping relation is obtained.

The storage configuration requirement refers to the requirement of a user on the hard disk configuration of the server, and in order to realize the self-adaptive adjustment of the hard disk topology, the storage configuration requirement can be determined by automatically detecting the change of the mapping relation of the hard disk topology. In an embodiment, the current hard disk topology mapping relationship refers to a mounting relationship between a hard disk and a central processing unit at a time when the current hard disk state information is acquired, and the initial hard disk topology mapping relationship refers to a mounting relationship between a hard disk and a central processing unit at a time immediately before the time when the current hard disk state information is acquired. When the hard disk configuration requirement is changed, whether the number of hard disks and/or the positions of the hard disks are changed or not can be known by comparing the current hard disk topology mapping relation with the initial hard disk topology mapping relation at the last moment, so that whether the storage configuration requirement is changed or not is automatically determined, when the storage configuration requirement is determined to be changed, what the number of hard disks and the positions of the hard disks are changed compared with the current hard disk topology mapping relation can be clarified according to the current hard disk topology mapping relation and the initial hard disk topology mapping relation, in order to ensure the optimal storage performance after configuration, the current hard disk topology mapping relation is optimized according to the changed storage configuration, and the optimal hard disk topology mapping relation is obtained, namely the optimal hard disk topology mapping relation is obtained.

S603: and determining optimized route information according to the optimized hard disk topology mapping relation, so that the link switch adjusts the connection relation between the uplink port and the downlink port according to the optimized route information.

When the optimal hard disk topology mapping relation is determined in the last step, that is, after the storage configuration requirement is determined to be changed, the mounting relation of which hard disk is adjusted, that is, which hard disk is adjusted from the current bus port of the CPU to the bus port designated by the optimal hard disk topology mapping relation. In order to realize efficient and simple storage configuration adjustment, the connection relation of the hard disk and the bus port is adjusted by adjusting the connection relation of the uplink port and the downlink port of the link switch instead of adjusting the connection relation of the cable. Based on this, this step determines the optimized routing information according to the optimized hard disk topology mapping relationship, that is, determines, according to the optimized hard disk topology mapping relationship, the bus port on which the hard disk to be adjusted is to be mounted, and determines, based on the connection relationship between the uplink port and the downlink port in the link switch at the current time and the cable connection relationship, which uplink port and which downlink port should be established, if the connection is currently already established, the port connection relationship is needed first. After the optimized route information is determined, the optimized route information is issued to the link switch, and after the link switch receives the optimized route information, the connection relation of the uplink port and the downlink port in the link switch is correspondingly and automatically adjusted, so that the reconnection of the bus link according to the hard disk configuration requirement change is realized.

In the technical scheme provided by the embodiment, whether the storage configuration requirement of the user of the server is changed is automatically determined by monitoring the hard disk change information of the server, after the storage configuration requirement of the server is changed, the optimal hard disk topology meeting the storage configuration requirement of the user is determined according to the storage configuration requirement of the user and the hard disk topology mapping relation, the optimized route information is determined according to the optimal hard disk topology mapping relation, and the link switch automatically adjusts the newly configured topology of the hard disk to be the optimal topology according to the optimized route information, so that the connection between the bus port of the central processing unit and the hard disk is automatically adjusted according to the current quantity of the hard disks installed on the server, the hard disk topology is enabled to be optimal, the storage configuration of the server can be simply and efficiently adjusted, and the storage performance of the user is guaranteed to be optimal.

It should be noted that, in the present invention, the steps are not strictly executed sequentially, so long as they conform to the logic sequence, the steps may be executed simultaneously, or may be executed according to a certain preset sequence, and fig. 6 is only a schematic manner, and is not meant to represent only such an execution sequence.

In the above embodiment, the present invention also provides an efficient determination method of the current hard disk topology mapping relationship, which may include the following steps:

Determining at least one hard disk to be demanded in an in-place state according to the current hard disk state information of the server; determining an initial connection relation between an uplink port and a downlink port of a link switch according to initial routing information at the previous moment; determining an uplink connection relation between an uplink port of the link switch and a bus port of a central processing unit of the main board and a downlink connection relation between a downlink port of the link switch and each hard disk according to the cable connection relation; and determining the mounting corresponding relation between each hard disk to be required and the bus port of the central processing unit according to each uplink connection relation and each downlink connection relation so as to obtain the current hard disk topology mapping relation.

The hard disk to be required is used for representing the hard disk currently required by a user, the initial connection relationship refers to the connection relationship between the uplink port and the downlink port recorded in the initial routing information, and the mounting corresponding relationship refers to which hard disk is mounted on which bus port of which CPU. For each on-site hard disk to be required, when the connection relation between the on-site hard disk to be required and the uplink port of the link switch is determined, the connection relation between the uplink port and the internal downlink port is determined, and after the connection relation between the downlink port and the bus port of the central processing unit of the main board is determined, the mounting corresponding relation between each hard disk to be required and the bus port of the central processing unit is determined, so that the current hard disk topology mapping relation is obtained.

For example, in order to improve the accuracy of storage configuration adjustment of the server, prevent the phenomenon that the hard disk hot maintenance mistakenly triggers topology remapping when the server normally operates and affects the normal use of the server by a user, based on the above embodiment, the method may further include the following:

constructing a hard disk topology remapping function configuration option in a user management interface of a baseboard management controller in advance; the configuration options of the hard disk topology remapping function comprise an opening option and a closing option; when a hard disk topology remapping function starting instruction is received, determining a current hard disk topology mapping relation according to current hard disk state information of a server, a cable connection relation and initial routing information of the last moment.

In this embodiment, the function of adaptive adjustment of the storage configuration of the server, that is, the hard disk topology remapping function defined in this embodiment, defaults to an off state, when in use, the operation and maintenance personnel may turn on the function in the user management interface of the baseboard management controller, and after the hard disk topology remapping function is turned on, the storage configuration adjustment process of the server is performed according to S601-S603 of the above embodiment.

Further, the cable connection relationship in the above embodiment may be stored in a designated location in advance, or may be uploaded to a designated location after the hard disk topology remapping function is turned on. As a convenient implementation manner, the cable configuration area may be previously constructed in a user management interface of the baseboard management controller; the cable configuration area includes cable connection relationship upload options; when a cable connection relation uploading instruction is received, the cable connection relation corresponding to the hard disk backboard is obtained through analyzing the cable connection relation uploading instruction, and the cable connection relation is stored under a preset path. Inevitably, the cable connection relationship of the server will change, and the user will need to re-modify the cable connection relationship, so that, in this embodiment, the cable connection relationship adjustment option may also be built in advance in the cable configuration area in the user management interface of the baseboard management controller; when a cable connection relation adjustment instruction is received, a new cable connection relation corresponding to the hard disk backboard is obtained by analyzing the cable connection relation adjustment instruction; the cable connection relation adjustment instruction includes, but is not limited to, modifying a cable connection relation and deleting the cable connection relation, and for the case of deleting the cable connection relation, the new cable connection relation may be a blank file or may be identification information for identifying the deleted cable connection relation, and the current cable connection relation under the preset path is updated according to the new cable connection relation.

Therefore, the embodiment can more efficiently determine the topological mapping relation of the hard disk, set the function starting by a manual interaction mode and support the real-time adjustment of the cable connection relation, and has better practicability.

The above embodiment does not limit how to optimize the current hard disk topology mapping relationship, and the present embodiment further provides an exemplary optimization method of the current hard disk topology mapping relationship, which may include the following:

determining a target mounting corresponding relation meeting a pre-built storage configuration performance tuning principle according to the current storage configuration information of the server and the hard disk configuration condition of the main board; and taking the target mounting corresponding relation as an optimized hard disk topology mapping relation.

The current storage configuration information refers to the total number of hard disks of the server at the current moment and the corresponding mounting corresponding relation of each on-site hard disk, and the data can be obtained according to the current hard disk topology mapping relation. The hard disk configuration condition includes the number of CPUs included in the server, the bus port included in each CPU, and the number of hard disks each port can mount. After the server leaves the factory, the hard disk configuration condition is determined, and the data can be obtained according to the hard disk configuration data of the server. The storage configuration performance tuning principle is a hard disk configuration principle preset by a user, and aims to determine a hard disk mounting relationship when the optimal storage performance is realized based on the number of hard disks on a current server. The user can flexibly set according to the actual application scene, and the realization of the invention is not affected.

For example, in this embodiment, the storage configuration performance tuning principle may be generated according to the same number of hard disks mounted on each central processing unit, and the same number of hard disks mounted on each bus port of the same central processing unit; and determining a target mounting corresponding relation according to the current storage configuration information of the server and the hard disk configuration condition of the main board based on the storage configuration performance tuning principle. In this embodiment, in order to avoid adding additional performance overhead and avoiding occurrence of a storage performance bottleneck problem, the storage configuration performance tuning principle is based on an equalization principle, that is, the number of hard disks mounted between different CPUs is the same, and the number of hard disks mounted on different bus ports under the same CPU is the same. For example, the server includes 12 hard disks and two CPUs, namely CPU0 and CPU1, each CPU includes a plurality of sets of pci e bus interfaces with x16 bandwidth, and the bandwidth of the pci e bus-based solid state hard disk is x4, so that one set of x16 buses may be connected to 4 hard disks, and typically one CPU includes 1 to 3 sets of x16 pci e bus interfaces for connecting the hard disks. In order to ensure that the hard disk performance of the server reaches the optimum, when the server performs Pcie topology design on the hard disk based on a storage configuration performance tuning principle, 12 hard disks are averagely hung on Pcie interfaces of two CPUs, if the hard disks are hung on CPU0, CPU1 needs to access CPU0 through a UPI bus between the CPUs when accessing data, and then accesses the hard disk hung on the CPU0 through the Pcie bus, so that extra performance cost is increased. Similarly, the hard disks are distributed as evenly as possible across different x16 ppie interfaces on the same CPU. For example, 6 hard disks are hung on CPU0, if 4 blocks are hung on ppie Port0, 2 blocks are hung on ppie Port 1, and if the performance of the hard disk is high, the performance bottleneck easily occurs on the hard disk on Port 0.

After determining the storage configuration performance tuning principle, the process of determining the mounting relationship between the hard disk and the CPU according to the storage configuration performance tuning principle may include: determining the total number of hard disk demands of a current server and the current mounting corresponding relation of each hard disk to be demanded according to the current hard disk topology mapping relation, and taking the total number of hard disk demands of the current server and the current mounting corresponding relation of each hard disk to be demanded as current storage configuration information; the method comprises the steps of obtaining the number of central processing units contained in a main board, the number of bus ports of each central processing unit and the port bandwidth, and taking the number of the bus ports and the port bandwidth as hard disk configuration conditions; based on the fact that the number of the mounted hard disks of each central processing unit is the same and the number of the mounted hard disks of different bus ports of the same central processing unit is the same, the hard disks to be adjusted for topological relation adjustment and the target bus ports of the mounted target central processing units of the hard disks to be adjusted are determined from the hard disks to be required. In this embodiment, the hard disk to be adjusted is a hard disk to be required, which needs to be adjusted in topology, the target cpu is a cpu on which the hard disk to be adjusted wants to mount, and the target bus port is a bus port of the target cpu, where the bus port is used to mount the hard disk to be adjusted.

Therefore, the storage configuration optimization method and the storage configuration optimization device can ensure that the storage performance of the server is optimal to the greatest extent after the storage configuration adjustment by optimizing according to the storage configuration performance optimization principle.

The above embodiment does not limit how to determine the optimized routing information, and this embodiment also provides an exemplary implementation manner of determining the optimized routing information according to the optimized hard disk topology mapping relationship, which may include the following:

determining an initial uplink port and an initial downlink port of a hard disk to be adjusted according to the initial routing information; determining a target uplink port corresponding to a target bus port of a target central processing unit according to the cable connection relation; the initial downlink port and the target uplink port are used as the current route information of the hard disk to be adjusted; and generating optimized route information according to the current route information of each hard disk to be adjusted.

In this embodiment, after determining the target bus port of the hard disk to be adjusted and the target central processing unit, the initial uplink port and the initial downlink port, which are correspondingly connected to the hard disk to be adjusted at the previous moment, are obtained from the initial routing information, and the uplink port connected to the target bus port at the current moment, that is, the target uplink port in this embodiment, is determined according to the cable connection relationship, and in order to implement the optimal hard disk topology mapping relationship, the connection relationship between the initial uplink port and the initial downlink port is required to be adjusted, and the target uplink port and the initial downlink port are connected, so that the hard disk to be adjusted is mounted on the target bus port. Correspondingly, the optimized route information is to record the connection relation between the target uplink port and the initial downlink port, process each hard disk to be adjusted according to the embodiment, and generate the optimized route information according to the target uplink port and the initial downlink port of all the hard disks to be adjusted. After the optimized route information is determined, the optimized route information is issued to the link switch, and after the link switch receives the optimized route information, the connection relation of the uplink port and the downlink port in the link switch is correspondingly and automatically adjusted, so that the bus link can be automatically and efficiently reconnected according to the change of the hard disk configuration requirement.

The above embodiment does not limit how to automatically detect whether the storage configuration requirement changes, and the present invention further provides an exemplary implementation manner of determining whether the storage configuration requirement of the server changes according to the current hard disk topology mapping relationship and the initial hard disk topology mapping relationship at the last moment, which may include the following contents:

determining a hard disk to be required at the current moment according to the current hard disk topology mapping relation; determining an initial hard disk to be demanded at the last moment according to the initial hard disk topology mapping relation; if the hard disk to be required at the current moment is different from the initial hard disk to be required, the storage configuration requirement of the server is changed.

In this embodiment, when at least one data difference exists between the initial hard disk to be required and the hard disk to be required, for example, the initial hard disk to be required is one hard disk more than the hard disk to be required, or one hard disk is less than the hard disk to be required, or the positions of the initial hard disk to be required and the hard disk to be required are changed, the storage configuration requirements of the server are all indicated to be changed, whether the storage configuration requirements of the server are changed is automatically determined through comparison of the current hard disk topology mapping relationship and the initial hard disk topology mapping relationship, so that the workload of server reconfiguration can be effectively improved, and the working efficiency and reliability of server reconfiguration are improved.

In order to further improve the adjustment efficiency of the server storage configuration, a table database can be constructed in advance; the table database comprises an initial hard disk topology mapping table, an initial routing table, a detection topology mapping table, an optimization topology mapping table and an optimization routing table; the initial hard disk topology mapping table is the first topology mapping table of the server or the mapping table after the last topology optimization iteration is performed due to the configuration, namely the optimization topology mapping table in the last adjustment process of the server storage configuration, so that the initial hard disk topology mapping table can be updated directly according to the optimization topology mapping table after the completion of the adjustment of the server storage configuration is detected, and the initial hard disk topology mapping table is updated according to the optimization topology mapping table after the link switch is detected to adjust the connection relation between the uplink port and the downlink port according to the optimization routing information. The initial routing table is used for storing initial routing information at the previous moment, the detection topology mapping table is used for storing the current hard disk topology mapping relation, and the detection topology mapping table is updated according to the current hard disk topology mapping relation obtained through the determination in the steps; the optimized topology mapping table is used for storing the optimized hard disk topology mapping relation, and the optimized topology mapping table can be updated according to the optimized hard disk topology mapping relation obtained through the steps; the optimized route table is used for storing optimized route information, and the optimized route table can be updated according to the optimized route information obtained through the determination in the steps. Further, since the initial routing information is the last routing information when the storage configuration of the server needs to be adjusted, after the adjustment process of the storage configuration of the server is completed, the optimized routing information is the initial routing information when the storage configuration of the server needs to be adjusted next time, so that after detecting that the link switch adjusts the connection relationship between the uplink port and the downlink port according to the optimized routing information, the optimized routing table can be directly used to update the initial routing table.

For example, the server currently includes 4 hard disks, the storage configuration requirement of the user is 2 disk configuration, the initial routing table, the detection topology mapping table, the optimization topology mapping table, and the optimization routing table are changed in the process that the storage configuration of the server is adjusted from the 4 disk configuration to the 2 disk configuration, wherein 1A, 2A, 3A, 4A are downlink ports of the link switch, 1B, 2B, 3B, 4B are uplink ports of the link switch, and CPU0_pe0_pcie [0,3] represents a Pcie port of CPU0, the port number is pe0_pcie [0,3], CPU0_pe1_pcie [0,3] represents a Pcie port of CPU0, the port number is pe1_pcie [0,3], CPU1_pe0_pcie [0,3] represents a Pcie port of CPU1, the port number is pe0_pcie [0,3], CPU1_pe1_pcie [0,3] represents a Pcie port of CPU0, and the port number is not shown as a bit number of the hard disk, [0 ] is shown in fig. 1, 3] is shown in the server:

reading an initial topology mapping table and an initial routing table from a table database, and combining to obtain a hard disk initial data record table shown in table 1:

table 1 hard disk initial data recording table

After the storage configuration requirement is adjusted to be 2 hard disks, the hard disk slot 1 and the hard disk slot 2 are inserted with hard disks, and the slot 3 and the slot 4 are empty, and accordingly, the detection topology mapping table can be expressed as:

Table 2 combination table of the detected topology mapping table and the initial routing table of the hard disk

According to the method described in the above embodiment, the storage configuration of the server is adjusted to obtain an optimized topology mapping table and an optimized routing table, where the optimized topology mapping table and the optimized routing table may be expressed as:

table 3 Combined table of optimized topology mapping table and optimized routing table for hard disk

As can be seen from the above, in this embodiment, the table database records the data in the adjustment process of the server storage configuration, and when the hard disk configuration changes, the system can automatically adjust the hard disk topology to an optimal state based on the table database, without manual operation, so that the workload of server reconfiguration is reduced, and the working efficiency and reliability of server reconfiguration are improved.

The invention also provides a corresponding device for the storage configuration adjustment method of the server, so that the method has more practicability. Wherein the device may be described separately from the functional module and the hardware. In the following description, a storage configuration adjustment device of a server according to the present invention is described, where the storage configuration adjustment device is configured to implement a storage configuration adjustment method of a server according to the present invention, and in this embodiment, the storage configuration adjustment device of a server may include or be divided into one or more program modules, where the one or more program modules are stored in a storage medium and executed by one or more processors, to implement a storage configuration adjustment method of a server according to the first embodiment of the present invention. Program modules in the present embodiment refer to a series of computer program instruction segments capable of performing a specific function, and are more suitable than programs themselves for describing the execution of the storage configuration adjustment apparatus of the server in the storage medium. The following description will specifically describe functions of each program module of the present embodiment, and a storage configuration adjustment device of the server described below and a storage configuration adjustment method of the server described above may be referred to correspondingly to each other.

Based on the angles of the functional modules, referring to fig. 7, fig. 7 is a block diagram of a storage configuration adjusting device of a server according to the embodiment, where the device is applied to a baseboard management controller, and may include the following functional modules:

the hard disk topology detection module 701 is configured to determine a current hard disk topology mapping relationship according to current hard disk state information of the server, a cable connection relationship, and initial routing information of a previous moment; each hard disk of the server is connected with a bus port of the central processing unit of the main board through a link switch positioned on the back plate of the hard disk.

The storage requirement change determining module 702 is configured to, when determining that the storage configuration requirement of the server changes according to the current hard disk topology mapping relationship and the initial hard disk topology mapping relationship at the previous moment, optimize the current hard disk topology mapping relationship to obtain an optimized hard disk topology mapping relationship; the hard disk topology mapping relationship represents the mounting corresponding relationship between each hard disk of the server and each central processing unit.

The hard disk topology optimization module 703 is configured to determine optimized routing information according to the optimized hard disk topology mapping relationship, so that the link switch adjusts the connection relationship between the uplink port and the downlink port according to the optimized routing information; the routing information is used for representing the connection relation between the uplink port and the downlink port in the link switch.

Illustratively, in some implementations of this embodiment, the hard disk topology detection module 701 may further be configured to:

determining an initial connection relation between an uplink port and a downlink port of a link switch according to initial routing information at the previous moment;

determining the uplink connection relation between the uplink port of the link switch and the bus port of the central processing unit of the main board according to the cable connection relation, and determining the downlink connection relation between the downlink port of the link switch and each hard disk;

As an exemplary implementation of the foregoing embodiment, the foregoing hard disk topology detection module 701 may further be configured to:

constructing a hard disk topology remapping function configuration option in a user management interface of a baseboard management controller in advance; the configuration options of the hard disk topology remapping function comprise an opening option and a closing option;

As another exemplary implementation of the foregoing embodiment, the foregoing hard disk topology detection module 701 may further be configured to:

constructing a cable configuration area in a user management interface of a baseboard management controller in advance; the cable configuration area includes cable connection relationship upload options;

when a cable connection relation adjustment instruction is received, a new cable connection relation corresponding to the hard disk backboard is obtained by analyzing the cable connection relation adjustment instruction;

Illustratively, in other implementations of this embodiment, the storage demand change determining module 702 may be further configured to:

As an exemplary implementation of the foregoing embodiment, the foregoing storage demand change determining module 702 may further be configured to:

As another exemplary implementation of the foregoing embodiment, the foregoing storage demand change determining module 702 may be further configured to:

determining the total number of hard disk demands of a current server and the current mounting corresponding relation of each hard disk to be demanded according to the current hard disk topology mapping relation, and taking the total number of hard disk demands of the current server and the current mounting corresponding relation of each hard disk to be demanded as current storage configuration information;

the method comprises the steps of obtaining the number of central processing units contained in a main board, the number of bus ports of each central processing unit and the port bandwidth, and taking the number of the bus ports and the port bandwidth as hard disk configuration conditions;

determining an initial uplink port and an initial downlink port of a hard disk to be adjusted according to the initial routing information;

determining a target uplink port corresponding to a target bus port of a target central processing unit according to the cable connection relation;

the initial downlink port and the target uplink port are used as the current route information of the hard disk to be adjusted;

Illustratively, in still other implementations of the present embodiment, the apparatus may further include a database for storing a pre-constructed table database; the table database comprises an initial routing table, an initial hard disk topology mapping table, a detection topology mapping table, an optimization topology mapping table and an optimization routing table; the initial routing table is used for storing initial routing information at the previous moment; the initial hard disk topology mapping table is used for storing the initial hard disk topology mapping relation at the last moment; the detection topology mapping table is updated according to the current hard disk topology mapping relation; the optimized topology mapping table is updated according to the optimized hard disk topology mapping relation; and updating the optimized routing table according to the optimized routing information.

As an exemplary implementation of the foregoing embodiment, the database further includes an updating unit configured to: and after detecting that the link switch adjusts the connection relation between the uplink port and the downlink port according to the optimized route information, updating the initial route table according to the optimized route table, and updating the initial hard disk topology mapping table according to the optimized topology mapping table.

Illustratively, in some implementations of this embodiment, the storage demand change determining module 702 may be further configured to:

determining a hard disk to be required at the current moment according to the current hard disk topology mapping relation;

if the hard disk to be required at the current moment is different from the initial hard disk to be required, the storage configuration requirement of the server is changed.

The functions of each functional module of the storage configuration adjustment device of the server in this embodiment may be specifically implemented according to the method in the foregoing method embodiment, and the specific implementation process may refer to the relevant description of the foregoing method embodiment, which is not repeated herein.

As can be seen from the above, the present embodiment can simply and efficiently adjust the storage configuration of the server, and ensure that the storage performance of the user is optimal.

The storage configuration adjusting device of the server is described from the perspective of a functional module, and further, the invention also provides an electronic device, which is described from the perspective of hardware. Fig. 8 is a schematic structural diagram of an electronic device according to an embodiment of the present invention. As shown in fig. 8, the electronic device comprises a memory 80 for storing a computer program; a processor 81 for implementing the steps of the storage configuration adjustment method of the server as mentioned in any of the above embodiments when executing a computer program.

Processor 81 may include one or more processing cores, such as a 4-core processor, an 8-core processor, and processor 81 may also be a controller, microcontroller, microprocessor, or other data processing chip, among others. The processor 81 may be implemented in at least one hardware form of DSP (Digital Signal Processing ), FPGA (Field-Programmable Gate Array, field programmable gate array), PLA (Programmable Logic Array ). The processor 81 may also include a main processor, which is a processor for processing data in an awake state, also called a CPU (Central Processing Unit ), and a coprocessor; a coprocessor is a low-power processor for processing data in a standby state. In some embodiments, the processor 81 may be integrated with a GPU (Graphics Processing Unit, graphics processor) for taking care of rendering and drawing of the content that the display screen is required to display. In some embodiments, the processor 81 may also include an AI (Artificial Intelligence ) processor for processing computing operations related to machine learning.

Memory 80 may include one or more computer-readable storage media, which may be non-transitory. Memory 80 may also include high-speed random access memory as well as non-volatile memory, such as one or more hard disk storage devices, flash memory storage devices. The memory 80 may in some embodiments be an internal storage unit of the electronic device, such as a hard disk of a server. The memory 80 may also be an external storage device of the electronic device, such as a plug-in hard disk provided on a server, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash Card (Flash Card), etc. in other embodiments. Further, the memory 80 may also include both internal storage units and external storage devices of the electronic device. The memory 80 may be used to store not only application software installed in an electronic device, but also various types of data, such as: code or the like of a program in the course of the storage configuration adjustment method of the execution server may also be used to temporarily store data that has been output or is to be output. In this embodiment, the memory 80 is at least used for storing a computer program 801, which, when loaded and executed by the processor 81, is capable of implementing the relevant steps of the storage configuration adjustment method of the server disclosed in any of the foregoing embodiments. In addition, the resources stored in the memory 80 may further include an operating system 802, data 803, and the like, where the storage manner may be transient storage or permanent storage. The operating system 802 may include Windows, unix, linux, among others. The data 803 may include, but is not limited to, data corresponding to a storage configuration adjustment result of the server, and the like.

In some embodiments, the electronic device may further include a display 82, an input/output interface 83, a communication interface 84, alternatively referred to as a network interface, a power supply 85, and a communication bus 86. Among other things, a display 82, an input output interface 83 such as a Keyboard (Keyboard) pertain to a user interface, which may also include standard wired interfaces, wireless interfaces, and the like. Alternatively, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch, or the like. The display may also be referred to as a display screen or display unit, as appropriate, for displaying information processed in the electronic device and for displaying a visual user interface. The communication interface 84 may illustratively include a wired interface and/or a wireless interface, such as a WI-FI interface, a bluetooth interface, etc., typically used to establish a communication connection between an electronic device and other electronic devices. The communication bus 86 may be a peripheral component interconnect standard (peripheral component interconnect, PCI) bus, or an extended industry standard architecture (extended industry standard architecture, EISA) bus, among others. The bus may be classified as an address bus, a data bus, a control bus, etc. For ease of illustration, only one thick line is shown in fig. 8, but not only one bus or one type of bus.

Those skilled in the art will appreciate that the configuration shown in fig. 8 is not limiting of the electronic device and may include more or fewer components than shown, for example, may also include sensors 87 to perform various functions.

The functions of each functional module of the electronic device in this embodiment may be specifically implemented according to the method in the foregoing method embodiment, and the specific implementation process may refer to the relevant description of the foregoing method embodiment, which is not repeated herein.

It will be appreciated that if the storage configuration adjustment method of the server in the above embodiment is implemented in the form of a software functional unit and sold or used as a separate product, it may be stored in a computer-readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied essentially or in part or all of the technical solution contributing to the related art, or may be embodied in the form of a software product stored in a storage medium, which performs all or part of the steps of the methods of the various embodiments of the present invention. And the aforementioned storage medium includes: a U disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (Random Access Memory, RAM), an electrically erasable programmable ROM, registers, a hard disk, a multimedia card, a card-type Memory (e.g., SD or DX Memory, etc.), a magnetic Memory, a removable disk, a CD-ROM, a magnetic disk, or an optical disk, etc., that can store program code.

Based on this, the present invention also provides a readable storage medium storing a computer program which when executed by a processor performs the steps of the storage configuration adjustment method of the server according to any one of the embodiments above.

The invention also provides a storage configuration adjustment system of the server, please refer to fig. 9, which may include a hard disk status monitoring subsystem 901, a routing subsystem 902 and a baseboard management controller 903; the hard disk state monitoring subsystem 901 and the routing subsystem 902 are disposed on a hard disk back plate of the server, the baseboard management controller 903 is disposed on a motherboard of the server, and the processor 81 may be built in the baseboard management controller. As shown in fig. 10, the hard disk state monitoring subsystem 901 is configured to send current hard disk state information of a server to the baseboard management controller 903; the baseboard management controller 903 is configured to implement the steps of the storage arrangement adjustment method of the server described in any one of the embodiments described above when executing the computer program stored in the memory; the routing subsystem 902 includes a link switch, which is configured to send initial routing information at a previous time to the baseboard management controller 903, and adjust a connection relationship between an uplink port and a downlink port according to optimized routing information sent by the baseboard management controller 903.

The baseboard management controller 903 is used as a management chip of the whole system, acquires information of hard disk change through a monitoring server, adaptively determines an optimal hard disk link topology according to new hard disk configuration, issues a command to the routing subsystem 902, the command carries optimized routing information, and the routing subsystem 902 adjusts the newly configured topology of the hard disk to the optimal topology according to the command. Taking the example that the CPU is connected to the hard disk through the pci bus, the link Switch of the routing subsystem 902 is a pci Switch (i.e. a high-speed serial computer expansion bus standard Switch), and the sideband signal connector is connected to the baseboard management controller through the I2C (i.e. an integrated circuit bus), the storage configuration adjustment procedure of the baseboard management controller to the server may include:

when an operation and maintenance person starts a user management interface, a hard disk topology remapping function, and the baseboard management controller 903 obtains the current on-site state of the hard disk to obtain hard disk state information; the baseboard management controller 903 reads the Pcie Switch register through the I2C to obtain the current Switch internal routing table, i.e., the initial routing table. And determining the topology mapping relation of the data link of the hard disk Pcie according to the state information of the hard disk, the initial routing table and the cable connection relation, and obtaining the detection topology mapping table. The baseboard management controller 903 compares the currently newly obtained detected topology map with the initial hard disk topology map, and if the topology does not change, the process ends. If the topology changes, the following operations are continued: and according to the fact that the number of the hard disks mounted among different CPUs is the same, the detection topology mapping table is optimized according to the fact that the number of the hard disks mounted among different Pcie ports under the same CPU is the same, an optimized topology mapping table is obtained, the optimized topology mapping table is updated into an initial hard disk topology mapping table for iteration, and an initial value is provided for next adjustment. The new routing table of the ppie Switch, i.e. which uplink port in the ppie Switch needs to be connected with which downlink port, is determined according to the optimized topology mapping table, which may be referred to as the optimized routing table. The optimized routing table is issued over the I2C bus into the Pcie Switch. And restarting the server to enable the new hard disk topology to be effective, and completing the optimization of the newly configured hard disk topology.

The functions of each functional module of the storage configuration adjustment system of the server according to the embodiment of the present invention may be specifically implemented according to the method in the embodiment of the method, and the specific implementation process may refer to the related description of the embodiment of the method, which is not repeated herein.

As can be seen from the above, the embodiment can realize the self-adaptive adjustment of the hard disk topology, and the system can automatically adjust the hard disk topology to the optimal state whenever the configuration of the hard disk changes, and ensure that the storage performance of the user reaches the optimal state, thereby avoiding manual operation, reducing the workload of server reconfiguration, and improving the working efficiency and reliability of server reconfiguration.

The above embodiment does not limit the structure of the hard disk state monitoring subsystem, and this embodiment also provides an exemplary implementation manner of the hard disk state monitoring subsystem 901, as shown in fig. 11, the main board includes two central processing units of CPU1 and CPU0, each central processing unit includes 4 groups of bus ports, which are ports [0,3], ports [4,7], ports [8, 11], ports [12, 15], the hard disk back board includes 12 hard disks, which are hard disks 1 to 12, respectively, correspondingly, there are 12 hard disk slots, each hard disk slot is provided with a first type connector, the uplink interfaces of the hard disk back board correspondingly include 12 uplink interfaces 1 to 12, each uplink interface is internally provided with an uplink interface connector, and the connector is connected with the bus port of the main board through a cable. The following may be included:

The hard disk state monitoring subsystem 901 comprises a hard disk in-place detector, a state register, a protocol converter and a sideband signal connector; one end of the hard disk in-place detector is connected in a first connector in a hard disk slot of the hard disk backboard, and the other end of the hard disk in-place detector is connected with the status register; one end of the protocol converter is connected with one end of the status register, the other end is connected with a sideband signal connector, and the sideband signal connector is connected with the baseboard management controller 903 through a target bus; the hard disk in-place detector is used for determining whether the corresponding hard disk is in place according to the level signal of the pin connected with the first type connector; the state register is used for generating current hard disk state information according to the current in-place state of each hard disk of the server; and the protocol converter is used for converting the current hard disk state information into data conforming to the target bus protocol and transmitting the data through the sideband signal connector. Illustratively, the sideband signal connector is coupled to the baseboard management controller via an integrated circuit bus; the protocol converter encapsulates the input/output extended data transmission protocol, is used for converting the current hard disk state information into bus data corresponding to the integrated circuit bus, and sends the bus data to the baseboard management controller 903.

In this embodiment, the hard disk state monitoring subsystem is a sensing unit of the whole system, and is configured to sense the current hard disk configuration and topology of the server, and when the hard disk configuration changes, the information after the hard disk configuration changes can be obtained and transferred to the processor of the baseboard management controller, so that the processor can use the information to perform adaptive adjustment of the storage configuration of the server. The first type of connector may be, for example, an SFF-8639 connector (a type of hard disk connector), after the server inserts the hard disk, the hard disk is connected to the hard disk back plate through the SFF-8639 connector on the back plate, and the target bus link, such as a pci data link, on the hard disk is connected to the uplink interface connector, such as a slot (i.e., a connector type) or an OCuLink connector (i.e., a connector type), on the hard disk back plate through the SFF-8639 connector and the printed circuit board of the hard disk back plate, and then the slot connector is connected to the target bus Port, such as a pci Port, of the CPU on the motherboard through a cable, so that the bus link, such as a pci link, on the hard disk is connected to the corresponding target bus Port, such as a pci Port, on the CPU. Because the hard disk backboard is unchanged, when the cable of the uplink interface connector such as the slimline connector on the backboard and the target bus Port such as the Pcie Port of the CPU of the main board are unchanged, the bus such as the Pcie link topology of the hard disk inserted in the slot of one SFF-8639 connector on the hard disk backboard is fixed. Therefore, when it can be identified which slot of the back plate is plugged into the hard disk or the connector of the slot is built in, such as an SFF-8639 connector, the topology of the hard disk can be determined according to the connection cable between the back plate and the main plate of the hard disk, that is, the connection of the hard disk to which Pcie port of which CPU is connected can be determined. The data of the status register is sent to the baseboard management controller 903 through a sideband signal connector, and needs to be converted into data of a target bus protocol by a protocol converter, when the baseboard management controller 903 and the sideband signal connector are connected through an I2C (Inter-Integrated Circuit, integrated circuit bus) bus, of course, the status register can also be connected through other buses, and the protocol converter can be built in with an io_expander (input-output expansion) protocol, so that status information of a hard disk slot can be converted into I2C bus data through the io_expander, and then transferred to the processor 81 of the baseboard management controller 903.

As an efficient and simple hard disk state detection mode, the total number of the hard disk in-place detectors is the same as the total number of the hard disk slots of the hard disk backboard, the state register comprises a plurality of registers, the number of the registers is the same as the total number of the hard disk slots, the registers are respectively and uniformly corresponding to each other, namely one hard disk in-place detector correspondingly detects the in-place state of one hard disk, and the in-place state detection result of the hard disk is recorded in the corresponding register. For example, the hard disk includes 12 hard disks 1, … … hard disks 12, and correspondingly, the CPLDs are also 12, and the CPLDs 1, … …, and 12. When the first complex programmable logic device such as CPLD1 detects that the first hard disk is in place, writing in the in-place identification information into a first register corresponding to the first hard disk; and when the second complex programmable logic device detects that the second hard disk is out of place, writing the out-of-place identification information into a first register corresponding to the second hard disk. The connection mode of the hard disk in-situ detector and the hard disk slot of the hard disk backboard can be as follows: the first level sampling pin of the hard disk in-place detector is connected with the hard disk in-place pin of the first type connector in the corresponding hard disk slot; the second level sampling pin of the hard disk in-place detector is connected with the hard disk type identification pin of the first type connector in the corresponding hard disk slot. Based on the connection mode, the hard disk in-place detector can determine whether the corresponding hard disk is in place or not according to the level signals of the first level sampling pin and the second level sampling pin based on the type of the hard disk inserted by the corresponding hard disk slot. For example, the hard disk bit detector uses a CPLD (Complex Programmable Logic Device ), taking the identification of the hard disk 1 on the slot 1 as an example, two pins of the present# (i.e., hard disk bit Pin) and ifdet# (i.e., hard disk type identification Pin) of the SFF-8639 connector on the backplane are pulled up respectively, and then connected to two level sampling pins adc_pin_1a and adc_pin1B of the CPLD. For Nvme hard disks, the pin of send# is floating and the ifdet# pin is grounded inside the hard disk. When no hard disk is plugged onto the SFF-8639 connector, the CPLD detects that the ADC_Pin_1A Pin is high, as is the ADC_Pin1B Pin. After the hard disk is inserted, the CPLD detects that the ADC_Pin_1A Pin is still high, but the ADC_Pin1B Pin signal is pulled low to ground by IFDET# of the hard disk, which goes low. The CPLD can determine whether the hard disk is inserted into the SFF-8639 connector by judging the level signals on the ADC_Pin_1A and the ADC_Pin_1B. If there is no hard disk insertion, the CPLD writes 0 in the hard disk_1 register, and if there is a hard disk insertion, the CPLD writes 1 in the hard disk_1 register. This forms a 12-bit register representing whether the corresponding hard disk slot has a hard disk insert. The status information of the hard disk slot is converted into I2C bus data by the hard disk status register through the io_expander, and is transferred to the processor 81 of the baseboard management controller 903, so that the processor 81 can obtain the current hard disk topology relationship through the bus such as the scie cable connection mode between the current hard disk backboard and the CPU of the motherboard and the hard disk in-place condition of the hard disk slot on the hard disk backboard, that is, which hard disk on the hard disk backboard is connected to which scie Port of which CPU.

The high-speed serial computer expansion bus standard bus port of the central processing unit is mounted on each hard disk of the server, and correspondingly, the link switch is the high-speed serial computer expansion bus standard switch, namely, the Pcie switch, and each downlink port of the Pcie switch is respectively connected with the first type connector in each hard disk slot of the hard disk backboard, and each uplink port is respectively connected with the high-speed serial computer expansion bus standard bus port through each uplink interface positioned on the hard disk backboard. The high-speed serial computer expansion bus standard switch is connected with the sideband signal connector through an integrated circuit bus; the high-speed serial computer expansion bus standard switch transmits the initial routing information to the baseboard management controller 903 through the sideband signal connector via the integrated circuit bus, and the baseboard management controller 903 transmits the optimized routing information to the high-speed serial computer expansion bus standard switch through the sideband signal connector. When the configuration of the hard disk changes, the hard disk state monitoring subsystem can acquire the position and topology change of the hard disk, and the baseboard management controller 903 re-plans the changed optimal topology and notifies the routing subsystem to change the hard disk topology. Route change is based on a Pcie switch implementation.

In this embodiment, as shown in fig. 12, the motherboard includes a baseboard management controller, which is connected to the CPU through a south bridge chip, and the motherboard includes two CPUs, CPU1 and CP0, each of which includes 4 sets of bus ports, ports [0,3], ports [4,7], ports [8, 11], ports [12, 15], respectively. The Pcie signal on the hard disk SFF-8639 connector on the traditional backboard is directly connected to the uplink interface connector through the backboard PCB wiring, the uplink interface connector is connected to the Pcie Port on the CPU of the main board through the cable, and when the hard disk topology is changed, the cable is required to be manually plugged and unplugged to change the Pcie topology. In the embodiment, a Pcie Switch circuit is added on the hard disk backboard, so that the path of the hard disk Pcie signal on the backboard is changed into a path from the SFF-8639 connector to the Pcie Switch circuit, and then from the Pcie Switch circuit to the backboard uplink interface connector. By implementing the change of the Pcie connection topology inside the Pcie Switch, the external cable does not need to be manually plugged in or plugged out. Taking the requirement of changing the 12 hard disk configuration to the 6 hard disk configuration as an example: when the 12-disk configuration is carried out, the Pcie data link of the hard disk_6 is connected to the downlink port_6A of the Pcie Switch, the 6A port inside the Switch is connected with the 6B port, the uplink port_6B is connected with the uplink interface connector 6, and finally the Pcie data link is connected with the PE0_Pcie [12, 15] port of the CPU of the main board through a cable. I.e. the initial topology is the pe0_pcie [12, 15] port mapping of hard disk_6 to CPU. When changing to a 6 hard disk configuration, to achieve an optimal topology, hard disk_6 needs to be hooked under the Pcie port of CPU 1. The processor 81 of the baseboard management controller 903 modifies the register of the Pcie Switch through the I2C bus to disconnect the downstream port_6a from the upstream port_6b and reconnect to the upstream port_12b in the Switch, because the user does not need the hard disk_12, and the ports 12A and 12B in the original Switch also need to be disconnected. The connection sequence of the external cables is kept unchanged, so that the Pcie data link of the hard disk_6 is connected to the Pcie port of the CPU1, topology remapping of the hard disk data link is completed, the external cables are not required to be manually plugged and unplugged in the whole topology change, the storage configuration of the server can be simply and efficiently adjusted, and the optimal storage performance of a user is ensured.

In this specification, each embodiment is described in a progressive manner, and each embodiment is mainly described in a different point from other embodiments, so that the same or similar parts between the embodiments are referred to each other. For the hardware including the apparatus, the system, the electronic device and the readable storage medium disclosed in the embodiments, since the hardware corresponds to the method disclosed in the embodiments, the description is relatively simple, and the relevant matters refer to the description of the method section.

Those of skill would further appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both, and that the various illustrative elements and steps are described above generally in terms of functionality in order to clearly illustrate the interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.

The method, the device, the system, the electronic equipment and the readable storage medium for adjusting the storage configuration of the server provided by the invention are described in detail. The principles and embodiments of the present invention have been described herein with reference to specific examples, the description of which is intended only to facilitate an understanding of the method of the present invention and its core ideas. It should be noted that, based on the embodiments of the present invention, all other embodiments obtained by a person skilled in the art without making any inventive effort fall within the scope of protection of the present invention. The invention is capable of numerous modifications and adaptations without departing from the principles of the invention, and such modifications and adaptations are intended to be within the scope of the invention as set forth in the claims.

Claims

1. A method for adjusting storage configuration of a server, which is applied to a baseboard management controller, wherein the process of adjusting the storage configuration of the server by the baseboard management controller comprises the following steps:

2. The method for adjusting storage configuration of a server according to claim 1, wherein determining the current hard disk topology mapping relationship according to the current hard disk state information of the server, the cable connection relationship, and the initial routing information of the last time comprises:

and determining the mounting corresponding relation between each hard disk to be required and the bus port of each central processing unit according to each uplink connection relation and each downlink connection relation so as to obtain the current hard disk topology mapping relation.

3. The method for adjusting storage configuration of a server according to claim 2, wherein determining the current hard disk topology mapping relationship according to the current hard disk state information of the server, the cable connection relationship, and the initial routing information of the last time comprises:

4. The method for adjusting storage configuration of a server according to claim 2, further comprising, before determining an uplink connection relationship between an uplink port of the link switch and a bus port of a central processor of the motherboard according to a cable connection relationship:

5. The method for adjusting a storage configuration of a server according to claim 4, further comprising, after the user management interface of the baseboard management controller constructs the cable configuration area:

6. The method for adjusting storage configuration of a server according to claim 1, wherein optimizing the current hard disk topology mapping relationship to obtain an optimized hard disk topology mapping relationship comprises:

7. The method for adjusting storage configuration of a server according to claim 6, wherein determining, according to current storage configuration information of the server and a hard disk configuration condition of the motherboard, a target mount correspondence that meets a pre-built storage configuration performance tuning principle includes:

8. The method for adjusting storage configuration of a server according to claim 6, wherein determining, according to current storage configuration information of the server and a hard disk configuration condition of the motherboard, a target mount correspondence that meets a pre-built storage configuration performance tuning principle includes:

9. The method for adjusting storage configuration of a server according to claim 8, wherein determining optimized routing information according to the optimized hard disk topology mapping relationship comprises:

10. The storage configuration adjustment method of a server according to claim 1, further comprising:

11. The storage configuration adjustment method of a server according to claim 10, further comprising, after updating the optimized routing table according to the optimized routing information:

12. The method for adjusting storage configuration of a server according to any one of claims 1 to 11, wherein determining that storage configuration requirements of the server have changed according to a current hard disk topology mapping relationship and an initial hard disk topology mapping relationship at a previous time includes:

13. A storage configuration adjustment device of a server, applied to a baseboard management controller, comprising:

the hard disk topology detection module is used for determining a current hard disk topology mapping relation according to current hard disk state information of the server, the cable connection relation and initial routing information of the last moment; each hard disk of the server is connected with a bus port of a central processing unit of the main board through a link switch positioned on a hard disk backboard; the cable connection relation represents a cable connection mode between the hard disk backboard and the central processing unit;

14. An electronic device comprising a processor and a memory, the processor being configured to implement the steps of the method for adjusting a storage configuration of a server according to any one of claims 1 to 12 when executing a computer program stored in the memory.

15. A readable storage medium, characterized in that the readable storage medium has stored thereon a computer program which, when executed by a processor, implements the steps of the storage configuration adjustment method of a server according to any of claims 1 to 12.

16. The storage configuration adjustment system of the server is characterized by comprising a hard disk state monitoring subsystem, a routing subsystem and a baseboard management controller;

the hard disk state monitoring subsystem is used for sending the current hard disk state information of the server to the baseboard management controller; the baseboard management controller implementing the steps of the storage configuration adjustment method of the server according to claim 1; the routing subsystem comprises a link switch, and is used for sending the initial routing information at the previous moment to the baseboard management controller, and adjusting the connection relation between the uplink port and the downlink port according to the optimized routing information sent by the baseboard management controller.

17. The storage configuration adjustment system of a server of claim 16, wherein the hard disk state monitoring subsystem comprises a hard disk in-place detector, a state register, a protocol converter, and a sideband signal connector;

18. The storage configuration adjustment system of claim 17, wherein the total number of hard disk in-place detectors is the same as the total number of hard disk slots of the hard disk backplane and corresponds one-to-one;

19. The storage configuration adjustment system of a server of claim 17, wherein the hard disk in-place detector is a complex programmable logic device; the state register comprises a plurality of registers, and each register corresponds to one hard disk of the server;

20. The memory configuration adjustment system of the server according to claim 17, characterized in that the sideband signal connector is connected to the baseboard management controller through an integrated circuit bus;

21. The storage configuration adjustment system of a server according to any one of claims 16 to 20, wherein each hard disk of the server is mounted on a high-speed serial computer expansion bus standard bus port of a central processing unit; the link switch is a high-speed serial computer expansion bus standard switch;

22. The memory configuration adjustment system of the server according to claim 21, wherein the high-speed serial computer expansion bus standard switch is connected to the sideband signal connector through an integrated circuit bus;