Storage Server, Multi-Storage Server System, and Switching Method of Storage Server

Abstract

The present invention provides a storage server, a multi-storage server system and a switching method for a storage server. The storage server includes a computing module, a monitoring module, a storage module, an interface module and a selection module; the interface module is used to connect to the upstream port of the target device; the monitoring module is communicatively connected to the computing module, the storage module, the interface module and the selection module respectively; the monitoring module is used to send a switching notification message to the target device through the interface module when it is determined that the computing module and / or the storage module fails; the monitoring module is further used to control the selection module to switch the gating direction while resetting the storage module. The storage server, the multi-storage server system and the switching method for the storage server provided by the present invention realize the automatic switching function of the upstream port of the storage module, so that the storage server working in the multi-server mode can automatically switch when encountering irreparable errors, and subsequent service work can be taken over by other storage servers.

Description

Technical Field

[0001] The present invention relates to the technical field of servers, and in particular, to a storage server, a multi-storage server system, and a switching method for a storage server. Background Art

[0002] With the rapid development of cloud computing and big data, the requirements for the storage capacity, rate, and security of storage servers are getting higher and higher. The common topology of current storage servers is Central Processing Unit (CPU)-Host Bus Adapter (HBA)-SAS Expander-Hard Disk Backplane. Among them, the HBA converts the PCIe signal of the CPU into a SAS signal, and the SAS signal is expanded through the SAS Expander to support a larger number of hard disks.

[0003] To improve the security of storage servers, there are two common methods: one is hard disk redundancy, that is, a part of the hard disks are used as backup hard disks to prevent data loss caused by the failure of the storage controller during data input. This method improves security by reducing the overall storage capacity of the server and has a high cost. The other is through cascading multiple SAS Expanders. This method focuses on solving the security problems caused by SAS Expander failures. In essence, it optimizes the signal transmission path through complex algorithms to improve the rate. This method has a relatively complex topology and is not conducive to system debugging. Therefore, existing storage servers all have the disadvantages of low security, complex algorithms, high system debugging difficulty, and high cost, resulting in low efficiency of standby devices taking over services when the storage server fails or goes offline. Summary of the Invention

[0004] The present invention provides a storage server, a multi-storage server system, and a switching method for a storage server, so as to solve the defect that the efficiency of standby devices taking over services is relatively low when the storage server fails or goes offline in the prior art.

[0005] The present invention provides a storage server, including a computing module, a monitoring module, a storage module, an interface module, and a selection module;

[0006] The interface module is used to connect to the upstream port of the target device;

[0007] The monitoring module is communicatively connected to the computing module, the storage module, the interface module, and the selection module respectively;

[0008] The monitoring module is used to send a switching notification message to the target device through the interface module when it is determined that the computing module and / or the storage module fails.

[0009] The monitoring module is further configured to control the selection module to switch the gating direction while controlling the storage module to reset; wherein, the gating direction includes a mutually exclusive first gating direction and a second gating direction;

[0010] The first gating direction is used to enable the storage module communicatively connected to the selection module to receive a first upstream signal sent from an upstream port of the target device through the interface module after reloading a first firmware FW;

[0011] The second gating direction is used to enable the storage module communicatively connected to the selection module to send a second upstream signal to the target device through an upstream port after reloading a second firmware FW;

[0012] Wherein, the first FW is obtained by the selection module when the first gating direction is in a connected state, and the second FW is obtained by the selection module when the second gating direction is in a connected state.

[0013] According to a storage server provided by the present invention, the selection module includes a dual multiplexer, a first chip and a second chip;

[0014] A first input terminal of the dual multiplexer is configured to receive a gating direction switching signal sent by the monitoring module;

[0015] A second input terminal of the dual multiplexer is configured to receive a serial peripheral interface chip select signal sent by the storage module;

[0016] The first chip is connected to a first output terminal of the dual multiplexer, and the second input terminal and the first output terminal form the first gating direction;

[0017] The second chip is connected to a second output terminal of the dual multiplexer, and the second input terminal and the second output terminal form the second gating direction;

[0018] The dual multiplexer is configured to control the serial peripheral interface chip select signal to obtain FW from an output to a corresponding chip along a corresponding gating direction according to the gating direction switching signal.

[0019] According to a storage server provided by the present invention, the computing module includes a central processing unit CPU and a host bus adapter HBA;

[0020] The HBA converts a PCIe signal sent by the CPU into an upstream SAS signal and then sends it to the storage module and the interface module.

[0021] A storage server provided by the present invention, the monitoring module includes a Baseboard Management Controller (BMC) and a logic device;

[0022] The BMC is configured to send a status monitoring message to the HBA. When it is determined that a failure has occurred based on the operation log fed back by the HBA, while sending a logic conversion message to the logic device, it also sends a switching notification message to the interface module;

[0023] The logic device is configured to, based on the logic conversion message, send the gating direction switching signal to the dual selector and send a reset signal to the storage module simultaneously.

[0024] A storage server provided by the present invention, the interface module includes a first interface, a second interface, and a third interface;

[0025] The first interface is configured to receive a first upstream signal sent by an upstream port of the target device;

[0026] The second interface is configured to send a second upstream signal sent by the HBA to the target device;

[0027] The third interface is configured to, when receiving the switching notification message sent by the BMC, send the switching notification message to the target device.

[0028] A storage server provided by the present invention, the storage module includes a SAS expansion card and a hard disk array;

[0029] The SAS expansion card is configured to, when reloading the first FW, receive the first upstream signal sent by the upstream port of the target device through the first interface;

[0030] The SAS expansion card is further configured to, when reloading the second FW, while sending the second upstream signal sent by the HBA to the target device through the second interface, expand the second upstream signal into N branch - corresponding branch SAS signals and send them to N hard disks corresponding to each branch in the hard disk array respectively.

[0031] The present invention further provides a multi - storage server system, including the first storage server and the second storage server as described above;

[0032] The third interface of the first storage server is communicatively connected to the third interface of the second storage server;

[0033] The first interface of the first storage server is communicatively connected to the second interface of the second storage server;

[0034] The second interface of the first storage server is communicatively connected to the first interface of the second storage server.

[0035] The present invention further provides a method for switching storage servers, including:

[0036] When the monitoring module determines that a storage module and / or a computing module fails based on the operation log, sending a switching notification message to a target device through the interface module;

[0037] While the monitoring module controls the reset of the storage module, controlling the selection module to switch the gating direction;

[0038] Wherein, the gating direction includes a mutually exclusive first gating direction and a second gating direction; the first gating direction is used for the storage module communicatively connected to the selection module to reload the first firmware FW and then receive a first upstream signal sent from the upstream port of the target device through the interface module; the second gating direction is used for the storage module communicatively connected to the selection module to reload the second firmware FW and then send a second upstream signal to the target device through the upstream port;

[0039] Wherein, the first FW is obtained by the selection module when the first gating direction is in a connected state, and the second FW is obtained by the selection module when the second gating direction is in a connected state.

[0040] The present invention further provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the program, the method for switching a storage server as described in any one of the above is implemented.

[0041] The present invention further provides a non-transitory computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the method for switching a storage server as described in any one of the above is implemented.

[0042] The storage server, multi-storage server system, and method for switching a storage server provided by the present invention are connected to the upstream port of a target device based on an interface module. When the monitoring module detects a failure of a computing module and / or a storage module, while sending a switching notification message to the target device through the interface module, it also controls the selection module to switch the gating direction, so that after the storage module is reset, it reloads the firmware corresponding to the switched gating direction, and uses the upstream port of the target device as the new upstream port of the storage module. The automatic switching function of the storage module's upstream port is realized, enabling the storage server operating in a multi-server mode to automatically switch when encountering irreparable errors, and allowing other storage servers to take over subsequent business work. It has the advantages of large capacity, low cost, simple topology, convenient debugging, and high security. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0044] Figure 1 is one of the schematic structural diagrams of the storage server provided by the present invention;

[0045] Figure 2 is another schematic structural diagram of the storage server provided by the present invention;

[0046] Figure 3 is the schematic structural diagram of the multi-storage server system provided by the present invention;

[0047] Figure 4 is one of the schematic flowcharts of the switching method of the storage server provided by the present invention;

[0048] Figure 5 is another schematic flowchart of the switching method of the storage server provided by the present invention;

[0049] Figure 6 is the schematic structural diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0050] To make the objectives, technical solutions, and advantages of the present invention clearer, the following will clearly and completely describe the technical solutions in the present invention with reference to the drawings in the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art without creative efforts based on the embodiments in the present invention fall within the scope of protection of the present invention.

[0051] The terms "first", "second", etc. in the specification of this application are used to distinguish similar objects and are not used to describe a specific order or sequence. It should be understood that such data can be interchanged under appropriate circumstances so that the embodiments of this application can be implemented in an order other than those illustrated or described herein, and the objects distinguished by "first", "second", etc. are generally of the same type, and the number of objects is not limited. For example, the first object can be one or more.

[0052] It should be understood that the terms used in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the specification of the present invention, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include the plural forms.

[0053] The terms "comprising" and "including" indicate the presence of the described features, wholes, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or their combinations.

[0054] Figure 1 It is one of the structural schematic diagrams of the storage server provided by the present invention. As Figure 1 shown, the storage server provided by the embodiment of the present invention includes a computing module 110, a monitoring module 120, a storage module 130, an interface module 140 and a selection module 150.

[0055] The interface module 140 is used to connect to the upstream port of the target device.

[0056] The monitoring module 120 is communicatively connected to the computing module 110, the storage module 130, the interface module 140 and the selection module 150 respectively.

[0057] The monitoring module 120 is used to send a switching notification message to the target device through the interface module 140 when it is determined that the computing module 110 and / or the storage module 130 fails.

[0058] The monitoring module 120 is further used to control the switching of the selection direction of the selection module 150 while controlling the reset of the storage module 130.

[0059] Wherein, the selection direction includes a mutually exclusive first selection direction and a second selection direction.

[0060] The first selection direction is used to enable the storage module 130 communicatively connected to the selection module 150 to receive the first upstream signal sent by the upstream port of the target device through the interface module 140 after reloading the first firmware FW.

[0061] The second selection direction is used to enable the storage module 130 communicatively connected to the selection module 150 to send a second upstream signal to the target device through the upstream port after reloading the second firmware FW.

[0062] Wherein, the first FW is obtained by the selection module 150 when the first selection direction is in a connected state, and the second FW is obtained by the selection module 150 when the second selection direction is in a connected state.

[0063] It should be noted that the target device refers to using its own storage server as the primary device and the standby server device other than this device.

[0064] The target device can be an ordinary storage server or another storage server with the same structure as the storage server.

[0065] Among them, the storage server establishes a signaling transmission channel with the target device through the internal port module 140.

[0066] Specifically, the storage server is composed of a computing module 110, a monitoring module 120, a storage module 130, an interface module 140, and a selection module 150.

[0067] The computing module 110 is responsible for computing and signal conversion, and sends the uplink data converted by the local machine to the storage module 130 or the interface module 140.

[0068] The monitoring module 120 is responsible for monitoring the operating status of the storage server. When the monitoring module 120 sends a monitoring signal to the computing module 110 and determines that the computing module 110 and / or the storage module 130 has an irreparable error according to the operation log fed back by the computing module 110, it sends a switching notification message to the target device through the interface module 140 to instruct the target device to prepare to take over the business work of the storage server.

[0069] Immediately afterwards, the monitoring module 120 sends a control signal A to the storage module 130 to instruct the storage module 130 to reset. At the same time, the monitoring module 120 sends a control signal B to the selection module 150 to instruct the selection module 150 to switch the selection direction and re-obtain the firmware (Firmware, FW). Furthermore, the storage module 130 in the faulty local Host (i.e., the storage server) is switched to another Host (i.e., the target device) to ensure the normal progress of business work.

[0070] The storage module 130 is responsible for signal expansion and data storage, expands the uplink signal of the computing module 110 into multiple paths, and transmits each path to the corresponding hard disk respectively.

[0071] The interface module 140 can receive the uplink data generated by the local Host, and when another Host fails, transmit the uplink data generated by the computing module 110 of the local Host to another Host for related business work.

[0072] The interface module 140 can also be connected to the upstream port of the storage module in another Host through a cable, so that when this Host does not fail, the storage module 130 selects the computing module 110 as the upstream port by loading the corresponding FW, and receives the upstream data sent from the upstream port in this Host.

[0073] Alternatively, when this Host fails, the storage module 130 selects the upstream port of another Host as the new upstream port by loading the corresponding FW, and receives the upstream data sent from the upstream port in another Host.

[0074] The interface module 140 communicatively connects the monitoring modules of the two Hosts. When a failure occurs in one Host, a switching notification message is sent by the local machine, and the other Host implements the service.

[0075] The selection module 150 is responsible for reloading the specified FW to implement the selection of the upstream port, where:

[0076] When the first gating direction in the selection module 150 is in a connected state, after loading the first FW from the storage chip corresponding to the first gating direction, the first FW is transmitted to the storage module 130, so that after the storage module 130 is reset, it reloads the first FW, uses the upstream port of the target device as the new upstream port, and receives the first upstream signal sent from the new upstream port through the interface module 140, so that the service can proceed normally.

[0077] When the second gating direction in the selection module 150 is in a connected state, after loading the second FW from the storage chip corresponding to the second gating direction, the second FW is transmitted to the storage module 130, so that after the storage module 130 is reset, it reloads the second FW, uses the computing module 110 of this machine as the new upstream port of the target device, and sends the second upstream signal to the target device through the interface module 140, so that the service can proceed normally.

[0078] Based on the interface module being connected to the upstream port of the target device, in the embodiment of the present invention, when the monitoring module detects a failure of the computing module and / or the storage module, while sending a switching notification message to the target device through the interface module, it also controls the selection module to switch the gating direction, so that after the storage module is reset, it reloads the firmware corresponding to the switched gating direction, and uses the upstream port of the target device as the new upstream port of the storage module. The automatic switching function of the storage module upstream port is realized, so that when the storage server working in the multi-server mode encounters an irreparable error, it can automatically switch, and other storage servers take over the subsequent service work. It has the advantages of large capacity, low cost, simple topology, convenient debugging, and high security.

[0079] Figure 2This is the second schematic diagram of the storage server provided by the present invention. As Figure 2 shown, on the basis of any of the above embodiments, the selection module 250 includes a dual multiplexer 251, a first chip 252, and a second chip 253.

[0080] The first input terminal of the dual multiplexer 251 is used to receive the strobe direction switching signal sent by the monitoring module 220.

[0081] The second input terminal of the dual multiplexer 251 is used to receive the serial peripheral interface chip select signal sent by the storage module 230.

[0082] The first chip 252 is connected to the first output terminal of the dual multiplexer 251, and the second input terminal and the first output terminal form a first strobe direction.

[0083] The second chip 253 is connected to the second output terminal of the dual multiplexer 251, and the second input terminal and the second output terminal form a second strobe direction.

[0084] The dual multiplexer 251 is used to control the serial peripheral interface chip select signal to be output to the corresponding chip to obtain FW along the corresponding strobe direction according to the strobe direction switching signal.

[0085] Specifically, the selection module 250 includes a dual multiplexer 251, a first chip 252, and a second chip 253. The control Pin S (i.e., the first input terminal) of the dual multiplexer 251 is connected to the monitoring module 220, and the strobe direction is selected by receiving the Flash_Selete signal (i.e., the strobe direction switching signal) sent by the monitoring module 220.

[0086] The control Pin A (i.e., the second input terminal) of the dual multiplexer 251 is connected to the storage module 130 to receive the SPI_CS signal (i.e., the serial peripheral interface chip select signal) output by the storage module 130, and the corresponding FW is obtained in combination with the strobe direction indicated by the Flash_Selete signal, where:

[0087] The first strobe direction is formed by the second input terminal and the first output terminal (i.e., B1) of the dual multiplexer 251. The first output terminal is communicatively connected to the first chip Flash1. When the dual multiplexer 251 outputs the received SPI_CS signal from the B1 terminal according to the strobe direction switching signal to obtain the SPI_CS1 signal, the first FW obtained from Flash1 is sent to the storage module 230.

[0088] The second strobe direction is formed by the second input terminal and the second output terminal (i.e., B2) of the dual-path selector 251. The second output terminal is communicatively connected to the second chip Flash2. So that when the dual-path selector 251 outputs the received SPI_CS signal from the B2 terminal according to the strobe direction switching signal to obtain the SPI_CS2 signal, the second FW obtained from Flash2 is sent to the storage module 230.

[0089] Based on the dual-path selector in the embodiment of the present invention, the strobe direction is controlled by the strobe direction switching signal sent by the monitoring module, so that the storage module is controlled to load the correspondingly stored firmware from the first chip or the second chip under the determined strobe direction through the serial peripheral interface chip select signal. It realizes starting from the specified FW by controlling the storage module, and realizes the selection of the upstream port of the storage module, so that when the storage server working in the multi-server mode encounters an irreparable error, it can automatically switch, and other storage servers take over the subsequent service work. It has the advantages of large capacity, low cost, simple topology, convenient debugging and high security.

[0090] Based on any of the above embodiments, the computing module 210 includes a central processing unit CPU211 and a host bus adapter HBA212.

[0091] The HBA212 converts the PCIe signal sent by the CPU211 into an upstream SAS signal and then sends it to the storage module 230 and the interface module 240.

[0092] Specifically, the computing module 210 includes a CPU211 and an HBA212. The HBA212 converts the PCIe signal sent by the CPU211 into an upstream SAS signal and then connects it to the storage module 230 and the interface module 240.

[0093] When the HBA212 sends the upstream SAS signal to the storage module 230 for the local Host to perform relevant service processes on the upstream data.

[0094] When the HBA212 sends the upstream SAS signal to the interface module 240, when another Host fails, the local Host supplies the received upstream data to another Host to perform relevant service processes.

[0095] Based on the HBA in the embodiment of the present invention, after converting the PCIe signal sent by the CPU into an upstream SAS signal, and sending the upstream SAS signal to the storage module and the interface module, in the multi-server mode, when any storage server encounters an irreparable error, the remaining storage servers can all provide upstream data as backup devices, which has the advantages of large capacity, low cost, simple topology, convenient debugging and high security.

[0096] Based on any of the above embodiments, the monitoring module 220 includes a baseboard management controller BMC221 and a logic device 222.

[0097] The BMC221 is configured to send a status monitoring message to the HBA212. When it is determined that a failure has occurred according to the operation log fed back by the HBA212, while sending a logic conversion message to the logic device 222, it also sends a switching notification message to the interface module 240.

[0098] The logic device 222 is configured to send a strobe direction switching signal to the dual multiplexer 251 and a reset signal to the storage module 230 based on the logic conversion message.

[0099] It should be noted that the logic device 222 is used to process the received data using the built-in service logic, and the embodiments of the present invention do not make specific limitations on this.

[0100] Logically, the logic device 222 is a complex programmable logic device (CPLD).

[0101] Specifically, the monitoring module 220 includes a baseboard management controller BMC221 and a logic device 222. In the initial stage of operation, the BMC221 continuously reads the operation log of the computing module 210 by sending a status monitoring message (i.e., the I2C2 signal) to the HBA212 to monitor the operation status of the computing module 210 and the storage module 230.

[0102] When the BMC221 determines that an irreparable failure has occurred in the computing module 210 and / or the storage module 230 according to the operation log, it sends a logic conversion message (I2C1 signal) to the logic device 222 to notify the logic device 222 that the local Host has a failure and execute the corresponding service logic. On the one hand, the logic device 222 sends a reset signal to the storage module 230 so that the storage module 230 is ready to load a new firmware. On the other hand, the logic device 222 sends a strobe direction switching signal for coping with the local failure situation to the dual multiplexer 251, so that the dual multiplexer 251 can obtain the corresponding firmware according to the strobe direction switching signal. After the storage module 230 reloads the firmware, the uplink interface of the target device is used as the new uplink interface to receive data.

[0103] When the BMC221 determines that an irreparable failure has occurred in the computing module 210 and / or the storage module 230 according to the operation log, it also needs to send a switching notification message to the interface module 240 at the same time to notify the target device to prepare to use its uplink interface as the new uplink interface of this Host.

[0104] In the embodiment of the present invention, the BMC monitors the health status by connecting to the HBA through I2C. When the BMC detects an irreparable error in the server, the logic device controls the gating direction of the dual-path switch and starts the storage module to reload the FW to switch the upstream Port. When in the multi-server mode, when any storage server encounters an irreparable error, the remaining storage servers can all serve as backup devices to provide upstream data, which has the advantages of large capacity, low cost, simple topology, convenient debugging, and high security.

[0105] Based on any of the above embodiments, the interface module 240 includes a first interface 241, a second interface 242, and a third interface 243.

[0106] The first interface 241 is used to receive a first upstream signal sent by the upstream port of the target device.

[0107] The second interface 242 is used to send a second upstream signal sent by the HBA 212 to the target device.

[0108] The third interface 243 is used to send a switching notification message to the target device when receiving a switching notification message sent by the BMC 221.

[0109] Specifically, the interface module 240 includes a first interface 241, a second interface 242, and a third interface 243, where:

[0110] The first interface 241 of the local Host is connected to the upstream port of the target device, and the third interface 243 is connected to the target device. When the local Host fails, first receive and transmit a switching notification message to the target device through the third interface 243 to notify the target device to prepare to use its upstream interface as an alternative upstream interface for switching. After the local Host reloads the new FW, receive the first upstream signal sent by the upstream port of the target device through the first interface 241.

[0111] The second interface 242 of the local Host is connected to the target device as an upstream port. When the target device fails, first receive the switching notification message sent by the target device through the third interface 243 to notify the local Host to prepare to use its upstream interface as an alternative upstream interface for the target device to switch. After the target device reloads the new FW, send the second upstream signal to the target device through the second interface 241.

[0112] Embodiments of the present invention respectively receive the first upstream signal of the HBA based on the first interface and the second interface in the interface module, connect to the upstream port of another Host through a cable, and also communicatively connect the BMCs of the two Hosts through the third interface for I2C3 signal to perform health monitoring on a single Host. It realizes that in a multi-server mode, when any storage server encounters an irreparable error, the remaining storage servers can all serve as backup devices to provide upstream data, having the advantages of large capacity, low cost, simple topology, convenient debugging, and high security.

[0113] Based on any of the above embodiments, the storage module 230 includes a SAS expansion card 231 and a hard disk array 232.

[0114] The SAS expansion card 231 is used to receive the first upstream signal sent by the upstream port of the target device through the first interface 241 when the first FW is reloaded.

[0115] The SAS expansion card 231 is also used to, when the second FW is reloaded, while sending the second upstream signal sent by the HBA 212 to the target device through the second interface 242, expand the second upstream signal into N branch corresponding branch SAS signals and respectively send them to N hard disks corresponding to each branch in the hard disk array 231.

[0116] Specifically, the storage module 230 includes a SAS expansion card 231 and a hard disk array 232.

[0117] When the local Host does not fail, directly expand the upstream SAS signal sent by the HBA 212 to the SAS expansion card 231 into N branch corresponding branch SAS signals, and respectively send the branch SAS signals to N hard disks corresponding to each branch in the hard disk array 232 to complete the data storage service.

[0118] When the local Host fails, if the first FW is obtained from the dual selector after the SAS expansion card 231 is reset, switch the upstream interface of the SAS expansion card 231 to the upstream port of the target device to receive the first upstream signal sent by the target device through the first interface 241, expand the first upstream signal into N branch corresponding branch SAS signals, and respectively send the branch SAS signals to N hard disks corresponding to each branch in the hard disk array 232 to complete the data storage service.

[0119] In the case of a target device failure, if the second FW is obtained from the dual selector after the SAS expander card 231 is reset, the HBA212 of the local Host is used as the new upstream port of the target device. While sending the second upstream signal to the target device through the second interface 242, the second upstream signal is expanded into N branch-corresponding branch SAS signals in the local Host, and the branch SAS signals are respectively sent to N hard disks corresponding to each branch in the hard disk array 232. While completing the data storage service of the local Host, the service of the target device can also be taken over.

[0120] In the normal operation of the embodiment of the present invention, based on the SAS expander card, the SAS signal of the computing module is expanded into multiple SAS signals and respectively connected to multiple hard disks. In the abnormal operation, the upstream interface of other devices is switched through the interface module to execute the service. It realizes that in the multi-server mode, when any storage server encounters an irreparable error, the remaining storage servers can all serve as backup devices to provide upstream data, and has the advantages of large capacity, low cost, simple topology, convenient debugging, and high security.

[0121] Figure 3 It is a schematic structural diagram of the multi-storage server system provided by the present invention. As Figure 3 shown, on the basis of any of the above embodiments, the system includes the first storage server 310 and the second storage server 320 as described above.

[0122] The third interface of the first storage server 310 is communicatively connected to the third interface of the second storage server 320.

[0123] The first interface of the first storage server 310 is communicatively connected to the second interface of the second storage server 320.

[0124] The second interface of the first storage server 310 is communicatively connected to the first interface of the second storage server 320.

[0125] Specifically, the multi-storage server system is at least composed of two or more storage servers as described above, and is connected pairwise through the interface modules of the storage servers.

[0126] Taking the multi-storage server system having the first storage server 310 and the second storage server 320 as an example below, the interface module 311 of the first storage server 310 is communicatively connected to the interface module 321 of the second storage server 320, where:

[0127] The third interface 311-3 of the first storage server 310 is communicatively connected to the third interface 321-3 of the second storage server 320, so that the BMCs of the two storage servers communicate through a switching notification message (I2C3 signal) to inform the other party when a failure occurs on one side.

[0128] The first interface 310-1 of the first storage server 310 is communicatively connected to the second interface 321-2 of the second storage server 320, so that the computing module of the second storage server 320 serves as a backup uplink interface for the first storage server 310. When the first storage server 310 fails, the first uplink signal sent by the second interface 321-2 of the second storage server 320 is obtained through the internal first interface 310-1.

[0129] The second interface 310-2 of the first storage server 310 is communicatively connected to the first interface 320-1 of the second storage server 320. So that the computing module of the first storage server 310 serves as a backup uplink interface for the second storage server 320. When the second storage server 320 fails, the second uplink signal sent by the second interface 311-2 of the first storage server 310 is obtained through the internal first interface 320-1.

[0130] Based on the interface module being connected to the uplink port of the target device, in the embodiment of the present invention, when the monitoring module detects a failure of the computing module and / or the storage module, while sending a switching notification message to the target device through the interface module, the selection module is also controlled to switch the gating direction, so that after the storage module is reset, the firmware corresponding to the switched gating direction is reloaded, and the uplink port of the target device is used as the new uplink port of the storage module. The automatic switching function of the uplink port of the storage module is realized, so that when the storage server operating in the multi-server mode encounters an irreparable error, it can automatically switch, and other storage servers take over the subsequent business work, which has the advantages of large capacity, low cost, simple topology, convenient debugging, and high security.

[0131] Figure 4 It is one of the flow diagrams of the switching method of the storage server provided by the present invention. As Figure 4 shown, based on any of the above embodiments, the switching method of the storage server includes: Step 401, when the monitoring module determines that the storage module and / or the computing module fails based on the operation log, send a switching notification message to the target device through the interface module.

[0132] It should be noted that the execution subject of the switching method of the storage server is the switching device of the storage server (its physical form can be a main board), or the storage server provided with the above main board.

[0133] Specifically, in step 401, after the monitoring module in the storage server sends a monitoring signal to the computing module, when it determines that an irreparable error has occurred in the computing module and / or the storage module based on the operation log feedback by the computing module, it sends a switching notification message to the target device through the interface module to instruct the target device to prepare to take over the business work of the storage server.

[0134] Step 402: While the monitoring module controls the storage module to reset, it controls the selection module to switch the gating direction.

[0135] Among them, the gating direction includes mutually exclusive first and second gating directions; the first gating direction is used to make the storage module communicatively connected to the selection module reload the first firmware FW, and then receive the first uplink signal sent by the uplink port of the target device through the interface module. The second gating direction is used to make the storage module communicatively connected to the selection module reload the second firmware FW, and then send the second uplink signal to the target device through the uplink port.

[0136] Among them, the first FW is obtained when the first gating direction in the selection module is in a connected state, and the second FW is obtained when the second gating direction in the selection module is in a connected state.

[0137] Specifically, in step 402, while the monitoring module in the storage server controls the storage module to reset, it controls the selection module to switch the gating direction and re-obtain the firmware. Furthermore, it switches the uplink port of the storage module in the faulty Host (i.e., the storage server) to another Host (i.e., the target device) to ensure the normal progress of business work. Among them:

[0138] When the first gating direction in the selection module is in a connected state, after loading the first FW from the storage chip corresponding to the first gating direction, the first FW is transmitted to the storage module so that the storage module reloads the first FW after reset, takes the uplink port of the target device as the new uplink port, and receives the first uplink signal sent by the new uplink port through the interface module to ensure the normal progress of business.

[0139] When the second gating direction in the selection module is in a connected state, after loading the second FW from the storage chip corresponding to the second gating direction, the second FW is transmitted to the storage module so that the storage module reloads the second FW after reset, takes the computing module of the local machine as the new uplink port of the target device, and sends the second uplink signal to the target device through the interface module to ensure the normal progress of business.

[0140] Exemplarily, Figure 5 is the second schematic diagram of the process of the switching method of the storage server provided by the present invention. As Figure 5As shown below, a specific implementation of the switching method of the storage server in the working mode of a dual-storage server system is given:

[0141] (1) The system operates in the dual-Host mode, and the monitoring module regularly checks the error log.

[0142] (2) When it is determined from the error log that an irreparable error has occurred in the storage module or the computing module of a certain Host.

[0143] (3) The interface module of the faulty Host notifies the other Host, enabling the other Host to prepare to use its computing module as the new upstream interface of the faulty Host and take over the storage module of the faulty Host.

[0144] (4) The monitoring module switches the gating direction of the dual-path selector of the faulty Host and triggers the SAS expansion card in the storage module to reload the FW and switch to the single-Host mode to receive the first upstream signal sent by the other Host for the storage module of the faulty Host to continue working.

[0145] In the embodiment of the present invention, based on the interface module being connected to the upstream port of the target device, when the monitoring module detects a failure in the computing module and / or the storage module, while sending a switching notification message to the target device through the interface module, it also controls the selection module to switch the gating direction, so that after the storage module is reset, it reloads the firmware corresponding to the switched gating direction, and uses the upstream port of the target device as the new upstream port of the storage module. The automatic switching function of the storage module upstream port is realized, so that when the storage server working in the multi-server mode encounters an irreparable error, it can automatically switch, and the subsequent service work is taken over by other storage servers, which has the advantages of large capacity, low cost, simple topology, convenient debugging, and high security.

[0146] Figure 6 An entity structure diagram of an electronic device is exemplified, as Figure 6As shown in the figure, the electronic device may include: a processor 610, a communications interface 620, a memory 630, and a communication bus 640. Among them, the processor 610, the communications interface 620, and the memory 630 complete communication with each other through the communication bus 640. The processor 610 may call the logical instructions in the memory 630 to execute the switching method of the storage server. The method includes: when the monitoring module determines that a storage module and / or a computing module fails based on the operation log, sending a switching notification message to the target device through the interface module; while the monitoring module controls the reset of the storage module, controlling the selection module to switch the gating direction; where the gating direction includes a mutually exclusive first gating direction and a second gating direction; the first gating direction is used to enable the storage module communicatively connected to the selection module to reload the first firmware FW and then receive the first uplink signal sent by the uplink port of the target device through the interface module; the second gating direction is used to enable the storage module communicatively connected to the selection module to reload the second firmware FW and then send the second uplink signal to the target device through the uplink port; where the first FW is obtained by the selection module when the first gating direction is in a connected state, and the second FW is obtained by the selection module when the second gating direction is in a connected state.

[0147] In addition, when the logical instructions in the above-mentioned memory 630 are implemented in the form of software functional units and sold or used as independent products, they may be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of the technical solution, may be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention. The foregoing storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical discs that can store program codes.

[0148] On the other hand, the present invention also provides a computer program product, which includes a computer program. The computer program can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the switching method of the storage server provided by the above-mentioned various methods. The method includes: when the monitoring module determines that a storage module and / or a computing module fails based on the operation log, sending a switching notification message to a target device through an interface module; while the monitoring module controls the reset of the storage module, controlling the selection module to switch the gating direction; wherein, the gating direction includes mutually exclusive first and second gating directions; the first gating direction is used to enable the storage module communicatively connected to the selection module to reload the first firmware FW and then receive a first upstream signal sent from the upstream port of the target device through the interface module; the second gating direction is used to enable the storage module communicatively connected to the selection module to reload the second firmware FW and then send a second upstream signal to the target device through the upstream port; wherein, the first FW is obtained when the selection module is in a connected state in the first gating direction, and the second FW is obtained when the selection module is in a connected state in the second gating direction.

[0149] In another aspect, the present invention also provides a non-transitory computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, it implements the switching method of the storage server provided by the above-mentioned various methods. The method includes: when the monitoring module determines that a storage module and / or a computing module fails based on the operation log, sending a switching notification message to a target device through an interface module; while the monitoring module controls the reset of the storage module, controlling the selection module to switch the gating direction; wherein, the gating direction includes mutually exclusive first and second gating directions; the first gating direction is used to enable the storage module communicatively connected to the selection module to reload the first firmware FW and then receive a first upstream signal sent from the upstream port of the target device through the interface module; the second gating direction is used to enable the storage module communicatively connected to the selection module to reload the second firmware FW and then send a second upstream signal to the target device through the upstream port; wherein, the first FW is obtained when the selection module is in a connected state in the first gating direction, and the second FW is obtained when the selection module is in a connected state in the second gating direction.

[0150] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art can understand and implement it without creative efforts.

[0151] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the essence of the above technical solution, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0152] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A storage server, characterized in that, It includes a calculation module, a monitoring module, a storage module, an interface module, and a selection module; The interface module is used to connect to the upstream port of the target device; the target device is the standby server of the storage server; The monitoring module is communicatively connected to the calculation module, the storage module, the interface module, and the selection module respectively; The monitoring module is used to send a switching notification message to the target device through the interface module when it is determined that the calculation module and / or the storage module fails; The monitoring module is further used to control the switching of the selection direction of the selection module while resetting the storage module; wherein, the selection direction includes a mutually exclusive first selection direction and a second selection direction; The first selection direction is used to enable the storage module communicatively connected to the selection module to receive the first upstream signal sent by the upstream port of the target device through the interface module after reloading the first firmware; The second selection direction is used to enable the storage module communicatively connected to the selection module to send a second upstream signal to the target device through the upstream port after reloading the second firmware; Wherein, the first firmware is obtained by the selection module when the first selection direction is in a connected state, and the second firmware is obtained by the selection module when the second selection direction is in a connected state; The selection module includes a dual multiplexer, a first chip, and a second chip; The first input terminal of the dual multiplexer is used to receive the selection direction switching signal sent by the monitoring module; The second input terminal of the dual multiplexer is used to receive the serial peripheral interface chip select signal sent by the storage module; The first chip is connected to the first output terminal of the dual multiplexer, and the second input terminal and the first output terminal constitute the first selection direction; The second chip is connected to the second output terminal of the dual multiplexer, and the second input terminal and the second output terminal constitute the second selection direction; The dual multiplexer is used to control the serial peripheral interface chip select signal to obtain firmware from the output to the corresponding chip along the corresponding selection direction according to the selection direction switching signal.

2. The storage server according to claim 1, wherein, The calculation module includes a central processing unit CPU and a host bus adapter HBA; The HBA converts the PCIe signal sent by the CPU into an upstream SAS signal and then sends it to the storage module and the interface module.

3. The storage server according to claim 2, wherein, The monitoring module includes a baseboard management controller BMC and a logic device; The BMC is used to send a status monitoring message to the HBA, and when it is determined that a failure has occurred according to the operation log fed back by the HBA, while sending a logic conversion message to the logic device, it also sends a switching notification message to the interface module; The logic device is used to send the selection direction switching signal to the dual multiplexer and send a reset signal to the storage module based on the logic conversion message.

4. The storage server according to claim 3, wherein The interface module includes a first interface, a second interface, and a third interface; The first interface is used to receive the first upstream signal sent by the upstream port of the target device; The second interface is used to send a second upstream signal sent by the HBA to the target device; The third interface is used to send the handover notification message to the target device when receiving the handover notification message sent by the BMC.

5. The storage server according to claim 4, characterized in that, The storage module includes a SAS expansion card and a hard disk array; The SAS expansion card is used to receive a first upstream signal sent by the upstream port of the target device through the first interface when reloading the first firmware; The SAS expansion card is further used to, when reloading the second firmware, while sending the second upstream signal sent by the HBA to the target device through the second interface, expand the second upstream signal into N branch-corresponding branch SAS signals and send them to N hard disks corresponding to each branch in the hard disk array respectively.

6. A multi-storage server system, characterized in that, It includes a first storage server and a second storage server; the first storage server and the second storage server are the storage servers according to any one of claims 1 to 5; The third interface of the first storage server is communicatively connected to the third interface of the second storage server; The first interface of the first storage server is communicatively connected to the second interface of the second storage server; The second interface of the first storage server is communicatively connected to the first interface of the second storage server.

7. A switching method for a storage server, characterized in that, It includes: When the monitoring module determines that a failure occurs in the storage module and / or the computing module based on the operation log, send a handover notification message to the target device through the interface module; The target device is a standby server of the storage server; The monitoring module controls the storage module to reset and at the same time controls the selection module to switch the gating direction; Wherein, the gating direction includes a mutually exclusive first gating direction and a second gating direction; the first gating direction is used to make the storage module communicatively connected to the selection module receive a first upstream signal sent by the upstream port of the target device through the interface module after reloading the first firmware; the second gating direction is used to make the storage module communicatively connected to the selection module send a second upstream signal to the target device through the upstream port after reloading the second firmware; Wherein, the first firmware is obtained by the selection module when the first gating direction is in a connected state, and the second firmware is obtained by the selection module when the second gating direction is in a connected state; The selection module includes a dual selector, a first chip and a second chip; The first input end of the dual selector is used to receive the gating direction switching signal sent by the monitoring module; The second input end of the dual selector is used to receive the serial peripheral interface chip select signal sent by the storage module; The first chip is connected to the first output end of the dual selector, and the second input end and the first output end form the first gating direction; The second chip is connected to the second output end of the dual selector, and the second input end and the second output end form the second gating direction; The dual-path selector is used to switch signals according to the gating direction, and control the chip select signal of the serial peripheral interface to obtain firmware from the corresponding chip along the corresponding gating direction from the output.

8. An electronic device, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the switching method of the storage server as described in claim 7.

9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the switching method of the storage server as described in claim 7.

Images