Storage link switching method and device based on expansion card and storage server

Abstract

The invention discloses a storage link switching method and device based on expansion cards and a storage server, and relates to the technical field of storage servers, each primary expansion card is provided with a main integrated circuit bus link and a standby integrated circuit bus link, and when any primary expansion card breaks down, the standby integrated circuit bus link is switched to the main integrated circuit bus link, and the standby integrated circuit bus link is switched to the standby integrated circuit bus link. And disconnecting the integrated circuit bus link of the failed first-stage expansion card, and taking over the second-stage expansion card corresponding to the failed first-stage expansion card through the standby integrated circuit bus link of the non-failed first-stage expansion card. And after it is determined that normal take-over can be carried out, the storage signals of the multiple secondary expansion cards corresponding to the failed primary expansion card are switched to the standby storage link of the primary expansion card which does not fail, and switching of the storage links is completed. The problem that under the condition that a storage server is complex, when storage link interruption or service interruption is caused by damage of any expansion card, the storage links can be switched in time, storage equipment failure is avoided, and data loss is avoided is solved.

Description

Technical Field

[0001] The present application relates to the technical field of storage servers, and particularly to a storage link switching method, device and storage server based on an expansion card. Background Art

[0002] In the era of explosive growth of data, the importance of the storage server field has become increasingly prominent. In order to achieve efficient management of storage devices, a storage array card has become an important component between the main control system of a storage server and hard disks. However, the number of hard disk interfaces provided by the original array card is limited, and many array cards only natively come with 8 hard disk interfaces, which cannot meet the user's need to expand the storage capacity.

[0003] Currently, related technologies connect more hard disks through an expansion card to increase the storage capacity of a storage server. However, with the continuous development of storage technologies, storage servers have become more and more complex. When any expansion card is damaged, resulting in a storage link interruption or service interruption, it is easy to cause storage device failure and data loss. Summary of the Invention

[0004] The present application provides a storage link switching method, device and storage server based on an expansion card, so as to at least solve the problem of storage device failure and data loss caused by any expansion card being damaged resulting in a storage link interruption or service interruption in related technologies.

[0005] The present application provides a storage link switching method based on an expansion card, which is applied to a storage server. The storage server includes: a plurality of first-level expansion cards, at least one main controller, a plurality of second-level expansion cards and a plurality of slave controllers. One first-level expansion card corresponds to a plurality of second-level expansion cards, and one second-level expansion card corresponds to one slave controller. The method for the main controller includes:

[0006] During the communication process with a plurality of first-level expansion cards, determining whether there is a faulty first-level expansion card;

[0007] If it is determined that there is a faulty first-level expansion card, disconnecting the integrated circuit bus link with the faulty first-level expansion card;

[0008] Sending an open standby integrated circuit bus link command to the non-faulty first-level expansion cards, so that the non-faulty first-level expansion cards open the standby integrated circuit bus link according to the open standby integrated circuit bus link command;

[0009] Sending a takeover request to the slave controllers of the plurality of second-level expansion cards corresponding to the faulty first-level expansion card through the standby integrated circuit bus link of the non-faulty first-level expansion cards, so that the slave controllers of the plurality of second-level expansion cards corresponding to the faulty first-level expansion card terminate responding to the commands of the faulty first-level expansion card;

[0010] Receive the takeover response sent by the slave controllers of multiple secondary expansion cards corresponding to the primary expansion card with a fault;

[0011] According to the takeover response, control the slave controllers of multiple secondary expansion cards corresponding to the faulty primary expansion card through the standby integrated circuit bus link of the non-faulty primary expansion card, and control the slave controllers of multiple secondary expansion cards corresponding to the non-faulty primary expansion card through the main integrated circuit bus link of the non-faulty primary expansion card;

[0012] Switch the storage signals of multiple secondary expansion cards corresponding to the faulty primary expansion card to the standby storage link of the non-faulty primary expansion card to complete the switching of the storage link.

[0013] This application also provides a storage link switching device based on an expansion card, which is applied to a storage server. The storage server includes: multiple primary expansion cards, at least one master controller, multiple secondary expansion cards, and multiple slave controllers. One primary expansion card corresponds to multiple secondary expansion cards, and one secondary expansion card corresponds to one slave controller. The device is used for the master controller and includes:

[0014] A judgment module, used to judge whether there is a faulty primary expansion card during the communication with multiple primary expansion cards;

[0015] A link disconnection module, used to disconnect the integrated circuit bus link with the faulty primary expansion card if it is determined that there is a faulty primary expansion card;

[0016] A sending module, used to send a command to open the standby integrated circuit bus link to the non-faulty primary expansion card, so that the non-faulty primary expansion card opens the standby integrated circuit bus link according to the command to open the standby integrated circuit bus link;

[0017] A termination response module, used to send a takeover request to the slave controllers of multiple secondary expansion cards corresponding to the faulty primary expansion card through the standby integrated circuit bus link of the non-faulty primary expansion card, so that the slave controllers of multiple secondary expansion cards corresponding to the faulty primary expansion card terminate the response to the commands of the faulty primary expansion card;

[0018] A receiving module, used to receive the takeover response sent by the slave controllers of multiple secondary expansion cards corresponding to the faulty primary expansion card;

[0019] A control module, used to control the slave controllers of multiple secondary expansion cards corresponding to the faulty primary expansion card according to the takeover response through the standby integrated circuit bus link of the non-faulty primary expansion card, and control the slave controllers of multiple secondary expansion cards corresponding to the non-faulty primary expansion card through the main integrated circuit bus link of the non-faulty primary expansion card;

[0020] A switching module, configured to switch the storage signals of multiple secondary expansion cards corresponding to a faulty primary expansion card to the backup storage link of the non-faulty primary expansion card, so as to complete the switching of the storage link.

[0021] The present application further provides a storage server, including: a memory for storing computer programs; a processor for implementing the steps of any of the above-mentioned storage link switching methods based on expansion cards when executing the computer programs.

[0022] The present application further provides a computer-readable storage medium, in which a computer program is stored. When the computer program is executed by a processor, the steps of any of the above-mentioned storage link switching methods based on expansion cards are implemented.

[0023] The present application further provides a computer program product, including a computer program. When the computer program is executed by a processor, the steps of any of the above-mentioned storage link switching methods based on expansion cards are implemented.

[0024] For the storage link switching method, device and storage server based on expansion cards provided by the present application, each primary expansion card has a main integrated circuit bus link and a backup integrated circuit bus link. When any primary expansion card fails, the integrated circuit bus link of the faulty primary expansion card is disconnected, and the secondary expansion cards corresponding to the faulty primary expansion card are taken over through the backup integrated circuit bus link of the non-faulty primary expansion card. After confirming that the takeover can be normal, the storage signals of multiple secondary expansion cards corresponding to the faulty primary expansion card are switched to the backup storage link of the non-faulty primary expansion card to complete the switching of the storage link. It solves the problem that when any expansion card is damaged, resulting in the interruption of the storage link or service interruption in the case of a complex storage server, the storage link can be switched in time to avoid the failure of the storage device and data loss. Description of the Drawings

[0025] In order to more clearly illustrate the embodiments of the present application, the following will briefly introduce the drawings required for the embodiments. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0026] Figure 1 It is the storage link diagram of the storage server with two-level expansion cards provided by the embodiment of the present application;

[0027] Figure 2 It is the integrated circuit bus link diagram of the storage server with two-level expansion cards provided by the embodiment of the present application;

[0028] Figure 3Schematic diagram of the storage link switching based on an expansion card provided by an embodiment of the present application;

[0029] Figure 4 Schematic diagram of the structure of the storage link switching device based on an expansion card provided by an embodiment of the present application;

[0030] Figure 5 Schematic diagram of the structure of the storage server provided by an embodiment of the present application. Detailed implementation manners

[0031] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present application without creative efforts shall fall within the protection scope of the present application.

[0032] It should be noted that in the description of the present application, the terms "include", "comprise" or any other variant thereof are intended to cover a non-exclusive inclusion, so that a process, method, article or device including a series of elements not only includes those elements but also includes other elements not expressly listed, or further includes elements inherent to such process, method, article or device. The terms "first", "second", etc. in the present application are used to distinguish similar objects and are not used to describe a specific order or sequence.

[0033] First, the terms involved in the present application are explained:

[0034] Integrated circuit bus link: A simple, two-wire bidirectional synchronous serial bus that uses a clock line and a data line to transfer information between two devices connected to the bus and exchange data between devices.

[0035] Host bus adapter card: A hardware device that provides a connection between a server and a storage device, mainly used to implement data transfer between a host system and a storage device.

[0036] To solve the problem that in the prior art, when any expansion card is damaged, resulting in a storage link interruption or a service interruption, it is easy to cause the storage device to fail and data loss, the embodiments of the present application propose the following technical concept: The inventor considered that in the face of a complex storage server, when any expansion card is damaged, resulting in a storage link interruption or a service interruption, it is easy to cause the storage device to fail and data loss. The inventor designed a primary integrated circuit bus link, a standby integrated circuit bus link, a primary storage link, and a standby storage link for each primary expansion card. When any primary expansion card fails, disconnect the integrated circuit bus link of the faulty primary expansion card, and take over the secondary expansion cards corresponding to the faulty primary expansion card through the standby integrated circuit bus link of the non-faulty primary expansion card. After confirming that the takeover can be carried out normally, switch the storage signals of the multiple secondary expansion cards corresponding to the faulty primary expansion card to the standby storage link of the non-faulty primary expansion card to complete the switching of the storage link. This solves the problem that when any expansion card is damaged, resulting in a storage link interruption or a service interruption in the case of a complex storage server, the storage link can be switched in time to avoid the failure of the storage device and data loss.

[0037] To enable those skilled in the art of the present technology to better understand the solution of the present application, the following further describes the present application in detail with reference to the accompanying drawings and specific embodiments.

[0038] Combined with the specific application environment architecture or specific hardware architecture on which the execution of the storage link switching method based on expansion cards depends, the specific application environment architecture or specific hardware architecture is described herein.

[0039] Refer to Figure 1 , Figure 1 which is the storage link diagram of the storage server with two-level expansion cards provided by the embodiments of the present application. As Figure 1 shown, the architecture of the storage server is a two-level expansion card structure, which expands the interface of the host bus adapter card and connects two primary expansion cards, namely expansion card 1 and expansion card 2. Each primary expansion card is connected to multiple secondary expansion cards. Among them, expansion card 1 is connected to two secondary expansion cards, namely expansion card 3 and expansion card 4, and storage devices are respectively hung under expansion card 3 and expansion card 4; expansion card 2 is connected to two secondary expansion cards, namely expansion card 5 and expansion card 6, and storage devices are respectively hung under expansion card 5 and expansion card 6.

[0040] Optionally, expansion card 1, expansion card 2, expansion card 3, expansion card 4, expansion card 5, and expansion card 6 all support connecting Serial Attached SCSI (SAS) devices and Serial ATA (SATA) devices.

[0041] Among them, the link between expansion card 1 and expansion cards 3 and 4 represents the main storage link of expansion card 1; the dotted link between expansion card 1 and expansion cards 5 and 6 represents the standby storage link of expansion card 1.

[0042] The link between expansion card 2 and expansion cards 5 and 6 represents the main storage link of expansion card 2; the dotted link between expansion card 2 and expansion cards 3 and 4 represents the standby storage link of expansion card 2.

[0043] Continue to refer to Figure 1 , the standby storage link of expansion card 1 is responsible for the services of expansion card 2 when expansion card 2 fails, that is, taking over expansion cards 5 and 6; the standby storage link of expansion card 2 is responsible for the services of expansion card 1 when expansion card 1 fails, that is, taking over expansion cards 3 and 4. To ensure that all storage devices remain in place and avoid the situation where half of the entire storage link fails due to a fault, thereby affecting the business.

[0044] Refer to Figure 2 , Figure 2 is the integrated circuit bus link diagram of the storage server with two-level expansion cards provided by the embodiment of the present application. As Figure 2 shown, the architecture of the storage server is a two-level expansion card structure, where the first-level expansion cards are expansion card 1 and expansion card 2, and the main controller is connected to expansion card 1 and expansion card 2 respectively through the integrated circuit bus link; expansion card 1 is connected to two second-level expansion cards, namely expansion card 3 and expansion card 4, and expansion card 2 is connected to two second-level expansion cards, namely expansion card 5 and expansion card 6. Each second-level expansion card is controlled by an independent slave controller.

[0045] Similar to the storage link, the link between expansion card 1 and expansion cards 3 and 4 through the slave controller represents the main integrated circuit bus link of expansion card 1; the dotted link between expansion card 1 and expansion cards 5 and 6 through the slave controller represents the standby integrated circuit bus link of expansion card 1.

[0046] The link between expansion card 2 and expansion cards 5 and 6 through the slave controller represents the main integrated circuit bus link of expansion card 2; the dotted link between expansion card 2 and expansion cards 3 and 4 through the slave controller represents the standby integrated circuit bus link of expansion card 2.

[0047] Optionally, the main controller can be a Complex Programmable Logic Device (CPLD), and the slave controller can also be a Complex Programmable Logic Device (CPLD).

[0048] Continue to refer to Figure 2 For the spare integrated circuit bus links of expansion card 1 and expansion card 2, when a takeover behavior occurs, the corresponding storage link still has a control link, avoiding the disconnection of the secondary expansion card and the corresponding storage device.

[0049] Continue to refer to Figure 1 and Figure 2 The architecture of the storage servers of the two-level expansion cards can achieve cascaded expansion of multiple links, and can continuously increase the links between the same levels or the overall link levels, increasing the scalability of the storage server and the overall storage space, and saving expensive computing resources at the upper layer.

[0050] Figure 3 The following is a schematic flowchart of the storage link switching based on the expansion card provided by the embodiment of the present application. As Figure 3 shown, the embodiment of the present application provides a storage link switching method based on an expansion card, which is applied to a storage server. The storage server includes: a plurality of primary expansion cards, at least one main controller, a plurality of secondary expansion cards, and a plurality of slave controllers. One primary expansion card corresponds to a plurality of secondary expansion cards, and one secondary expansion card corresponds to one slave controller. The method is used for the main controller, and the method is described in detail as follows:

[0051] S201: During the communication with a plurality of primary expansion cards, determine whether there is a faulty primary expansion card.

[0052] Specifically, the determination method is: during the communication with a plurality of primary expansion cards, if a failure status signal actively sent by any one of the primary expansion cards is received, it is determined that there is a faulty primary expansion card; or / and during the communication with a plurality of primary expansion cards, send a command to the plurality of primary expansion cards so that the plurality of primary expansion cards respond to the command; if no response sent by any one of the primary expansion cards is received, then continuously send the command a preset number of times to any one of the primary expansion cards after a preset time period. If no response sent by any one of the primary expansion cards is received, it is determined that there is a faulty primary expansion card.

[0053] Optionally, the failure status signal can be fail, and the preset number of times can be 3 times.

[0054] S202: If it is determined that there is a faulty primary expansion card, disconnect the integrated circuit bus link with the faulty primary expansion card.

[0055] In this embodiment, the spare integrated circuit bus links of each primary expansion card are default in the closed state.

[0056] Exemplarily, taking the expansion card 1 in Figure 2 as an example of a fault, the subsequent steps in this embodiment are all based on Figure 2Take the failure of the expansion card 1 in it as an example for introduction. If the expansion card 1 fails, disconnect the integrated circuit bus link between the main controller and the expansion card 1 and set it to the hung state.

[0057] S203: Send a command to open the standby integrated circuit bus link to the first-level expansion card that has not failed, so that the first-level expansion card that has not failed opens the standby integrated circuit bus link according to the command to open the standby integrated circuit bus link.

[0058] Exemplarily, send a command to open the standby integrated circuit bus link to the expansion card 2, so that the expansion card 2 opens the standby integrated circuit bus link.

[0059] S204: Send a takeover request to the slave controllers of multiple second-level expansion cards corresponding to the failed first-level expansion card through the standby integrated circuit bus link of the first-level expansion card that has not failed, so that the slave controllers of multiple second-level expansion cards corresponding to the failed first-level expansion card terminate responding to the commands of the failed first-level expansion card.

[0060] In this embodiment, when any first-level expansion card fails, the main controller disconnects the integrated circuit bus link with the failed first-level expansion card, but the main integrated circuit bus link from the failed first-level expansion card to the slave controllers of the corresponding second-level expansion cards is not faulty. Therefore, from the moment when the takeover request is sent from the first-level expansion card that has not failed until the takeover response sent by the slave controllers of multiple second-level expansion cards corresponding to the failed first-level expansion card is received, the slave controllers of multiple second-level expansion cards corresponding to the failed first-level expansion card may receive commands sent by two integrated circuit bus links. One is the command sent by the failed first-level expansion card through the main integrated circuit bus link, and the other is the takeover request sent by the first-level expansion card that has not failed through the standby integrated circuit bus link. To avoid this conflict, when the slave controller of the second-level expansion card corresponding to the failed first-level expansion card receives the takeover request, it terminates responding to the commands of the failed first-level expansion card.

[0061] Exemplarily, when the expansion card 1 fails, the main controller disconnects the integrated circuit bus link with the expansion card 1, but the main integrated circuit bus links from the expansion card 1 to the slave controllers of the expansion cards 3 and 4 are not faulty. Therefore, from the moment when the takeover request is sent from the expansion card 2 until the takeover response sent by the slave controllers of the expansion cards 3 and 4 is received, the slave controllers of the expansion cards 3 and 4 may receive commands sent by two integrated circuit bus links. One is the command sent by the expansion card 1 through the main integrated circuit bus link, and the other is the takeover request sent by the expansion card 2 through the standby integrated circuit bus link. To avoid this conflict, when the slave controllers of the expansion cards 3 and 4 receive the takeover request, they terminate responding to the commands of the expansion card 1.

[0062] S205: Receive takeover responses sent by slave controllers of multiple secondary expansion cards corresponding to the failed primary expansion card.

[0063] S206: According to the takeover responses, control the slave controllers of multiple secondary expansion cards corresponding to the failed primary expansion card through the standby integrated circuit bus link of the non-failed primary expansion card, and control the slave controllers of multiple secondary expansion cards corresponding to the non-failed primary expansion card through the primary integrated circuit bus link of the non-failed primary expansion card.

[0064] Exemplarily, after expansion card 2 receives takeover responses sent by the slave controllers of expansion cards 3 and 4, expansion card 2 controls the slave controllers of expansion cards 3 and 4 through the standby integrated circuit bus link, and at the same time, expansion card 2 continues to control the slave controllers of expansion cards 5 and 6 through the primary integrated circuit bus link.

[0065] S207: Switch the storage signals of multiple secondary expansion cards corresponding to the failed primary expansion card to the standby storage link of the non-failed primary expansion card to complete the switching of the storage link.

[0066] Exemplarily, switch the storage signals of expansion cards 3 and 4 to the standby storage link of expansion card 2.

[0067] In summary, when any primary expansion card fails, disconnect the integrated circuit bus link with the failed primary expansion card, and take over the secondary expansion cards corresponding to the failed primary expansion card through the standby integrated circuit bus link of the non-failed primary expansion card. After determining that the takeover can be completed normally, switch the storage signals of multiple secondary expansion cards corresponding to the failed primary expansion card to the standby storage link of the non-failed primary expansion card to complete the switching of the storage link. This solves the problem that when any expansion card is damaged, resulting in a storage link interruption or service interruption in a complex storage server scenario, the storage link can be switched in a timely manner to avoid storage device failure and data loss. In addition, when the slave controller of a secondary expansion card corresponding to the failed primary expansion card receives a takeover request, it stops responding to the commands of the failed primary expansion card, avoiding abnormal storage link switching caused by command conflicts.

[0068] In an embodiment of the present application, the storage server further includes a baseboard management controller. After the storage link switching is completed, the main controller sends a switching completion signal to the baseboard management controller, so that the baseboard management controller saves the fault information and issues an alarm signal to remind the operation and maintenance personnel to replace the failed primary expansion card as soon as possible.

[0069] In summary, the main controller sends the switching completion signal to the baseboard management controller, and through the baseboard management controller, it promptly notifies the occurrence of the storage link switching and the fault situation. On the one hand, it shortens the time for fault discovery, and on the other hand, it reminds the operation and maintenance personnel to promptly replace the faulty expansion card and resume the normal operation state as soon as possible.

[0070] In an embodiment of the present application, before executing the storage link switching method based on the expansion card, it is necessary to perform link tests on the main integrated circuit bus link and the standby integrated circuit bus link of each first-level expansion card. The link test includes a test preparation stage, a test stage, and a test end stage to ensure the stability of the link, which is described in detail as follows:

[0071] Specifically, the test preparation stage includes steps S301 to S303:

[0072] S301: Send a control application with a link stress test request flag to each first-level expansion card, so that each first-level expansion card sends the control application with the link stress test request flag to the slave controllers of the multiple second-level expansion cards corresponding to it through the main integrated circuit bus link, so that the slave controllers of the multiple second-level expansion cards corresponding to each first-level expansion card open the upstream standby integrated circuit bus link and send the ready state signal to each first-level expansion card, so that each first-level expansion card opens the downstream standby integrated circuit bus link.

[0073] In this embodiment, after receiving the control application with the link stress test request flag, the slave controllers of the multiple second-level expansion cards corresponding to each first-level expansion card open the receiving port of the upstream standby integrated circuit bus link and send the ready state signal to inform each first-level expansion card that it is ready. Each first-level expansion card opens the downstream standby integrated circuit bus link. At this time, both the main integrated circuit bus link and the standby integrated circuit bus link of each first-level expansion card are in the open state.

[0074] S302: Receive the ready state signal sent by each first-level expansion card.

[0075] S303: Send the ready state signal to the baseboard management controller to complete the test preparation stage.

[0076] Specifically, the test stage includes steps S304 to S306:

[0077] S304: Receive the in-position information query command sent by the baseboard management controller.

[0078] In this embodiment, the baseboard management controller sends a command to repeatedly query the in-position information of the first-level expansion card to the main controller, and sets the interval for querying each first-level expansion card each time within 0.1 second.

[0079] S305: Send the in-position information query command to each first-level expansion card so that each first-level expansion card performs the following steps: According to the in-position information query command, obtain the in-position information; Through the main integrated circuit bus link, send the flag bit of each first-level expansion card and the in-position information query command to the slave controllers of multiple second-level expansion cards corresponding to each first-level expansion card, so that the slave controllers of each second-level expansion card corresponding to each first-level expansion card send the in-position information of each second-level expansion card to the first-level expansion card corresponding to the flag bit through the main integrated circuit bus link; Through the standby integrated circuit bus link, send the flag bit of each first-level expansion card and the temperature query command to the slave controllers of multiple second-level expansion cards corresponding to the remaining first-level expansion cards, so that the slave controllers of each second-level expansion card corresponding to the remaining first-level expansion cards send the temperature information of each second-level expansion card to the first-level expansion card corresponding to the flag bit through the standby integrated circuit bus link.

[0080] Optionally, the in-position information query command sent to the slave controllers of multiple second-level expansion cards corresponding to each first-level expansion card through the main integrated circuit bus link can set the query interval time within 0.2 seconds; The temperature query command sent to the slave controllers of multiple second-level expansion cards corresponding to the remaining first-level expansion cards through the standby integrated circuit bus link can set the query interval time within 0.2 seconds.

[0081] Exemplarily, send the in-position information query command to Expansion Card 1 and Expansion Card 2 to Figure 2 Taking Expansion Card 1 in as an example, Expansion Card 1 obtains the in-position information according to the bit information query command. Expansion Card 1 sends the flag bit of Expansion Card 1 and the in-position information query command to the slave controllers of Expansion Card 3 and Expansion Card 4 through the main integrated circuit bus link. The slave controllers of Expansion Card 3 and Expansion Card 4 respectively send the in-position information to Expansion Card 1 through the main integrated circuit bus link; Through the standby integrated circuit bus link of Expansion Card 1, send the flag bit of Expansion Card 1 and the temperature query command to the slave controllers of Expansion Card 5 and Expansion Card 6. The slave controllers of Expansion Card 5 and Expansion Card 6 send the temperature information to Expansion Card 1 through the standby integrated circuit bus link.

[0082] S306: Receive the in-position information of each first-level card, the in-position information of each second-level expansion card, and the temperature information of each second-level expansion card sent by each first-level expansion card.

[0083] Specifically, the test end stage includes steps S307~S310:

[0084] S307: After reaching the preset test time, send a stop command to each first-level expansion card so that each first-level expansion card stops sending the flag bit, in-position information query command, and temperature query command of each first-level expansion card.

[0085] S308: Send a control application with a link stress test stop flag to each first-level expansion card, so that each first-level expansion card sends the control application with the link stress test stop flag to the slave controllers of multiple second-level expansion cards corresponding to each first-level expansion card through the main integrated circuit bus link; so that the slave controllers of multiple second-level expansion cards corresponding to each first-level expansion card close the upstream standby integrated circuit bus link and send a completion status signal to each first-level expansion card; so that each first-level expansion card closes the downstream standby integrated circuit bus link.

[0086] In this embodiment, after receiving the control application with the link stress test stop flag, the slave controllers of multiple second-level expansion cards corresponding to each first-level expansion card close the receiving ports of the upstream standby integrated circuit bus link.

[0087] S309: Receive the completion status signals sent by each first-level expansion card.

[0088] S310: Send the completion status signal to the baseboard management controller to complete the test end phase.

[0089] In this embodiment, after the test end phase is completed, the main integrated circuit bus links of each first-level expansion card are all in the open state, and the standby integrated circuit bus links of each first-level expansion card are all in the closed state.

[0090] In summary, testing the main integrated circuit bus links and standby integrated circuit bus links of each first-level expansion card ensures the stability of the main integrated circuit bus links and standby integrated circuit bus links, providing a basis for the switching of the storage link. In addition, testing the main integrated circuit bus links and standby integrated circuit bus links simultaneously reduces the test time on the one hand, and on the other hand, avoids resource shortages caused by all query commands being issued by the baseboard control manager, and distributes the test pressure to the main controller and each slave controller. In addition, there is no need to add test tools and test links, reducing the waste of test resources.

[0091] In an embodiment of the present application, the storage server further includes: a host bus adapter card and multiple storage devices; one second-level expansion card corresponds to one storage device; when no failure occurs in each first-level expansion card, the standby storage links of each first-level expansion card have enabling conditions. In this embodiment, on the premise that the main integrated circuit bus links and standby integrated circuit bus links of each first-level expansion card have been tested, the storage link is tested as follows:

[0092] S401: Send an open standby storage link command to each first-level expansion card, so that each first-level expansion card opens the standby storage link according to the standby storage link command.

[0093] In this embodiment, the standby storage links of each first-level expansion card are all in an open state.

[0094] S402: Send a command to close the main storage link to each first-level expansion card, so that each first-level expansion card sends the command to close the main storage link to the slave controllers of multiple slave second-level expansion cards corresponding to it through the main integrated circuit bus link, so that the slave controllers of multiple slave second-level expansion cards corresponding to each first-level expansion card close the main storage link according to the command to close the main storage link.

[0095] In this embodiment, the main storage links of each first-level expansion card are all in a closed state.

[0096] S403: Receive read / write instructions sent by the host bus adapter card.

[0097] S404: Send the read / write instructions to each first-level expansion card, so that each first-level expansion card sends the read / write instructions to the slave controllers of multiple second-level expansion cards corresponding to the other first-level expansion cards through the standby storage link, so that the slave controllers of multiple second-level expansion cards corresponding to the other first-level expansion cards send the read / write instructions to the corresponding storage devices, so that the storage devices perform read / write operations according to the read / write instructions, and send the return values of the read / write instructions to the storage server, so that the storage server judges whether the standby storage links of each first-level expansion card are normal according to the return values.

[0098] Exemplarily, taking Figure 2 expansion card 1 in as an example, send the read / write instructions to expansion card 1, so that expansion card 1 sends the read / write instructions to the slave controllers of expansion cards 5 and 6 corresponding to expansion card 2 through the standby storage link; the slave controllers of expansion cards 5 and 6 send the read / write instructions to the corresponding storage devices, so that the storage devices perform read / write operations according to the read / write instructions, and send the return values of the read / write instructions to the storage server, so that the storage server judges whether the standby storage links of each first-level expansion card are normal according to the return values.

[0099] In summary, by closing the main storage links of each first-level expansion card and opening the standby storage links, the test focuses on the standby storage links. After the storage device performs read / write operations, it provides the return values of the read / write commands to the storage server, which enables testers to directly obtain the results of data read / write. Through the analysis and verification of the return values, it is possible to accurately judge whether the data is correct on the standby storage link, whether there is data corruption or loss, etc., thus ensuring the integrity and accuracy of the data.

[0100] Through the description of the above embodiments, those skilled in the art can clearly understand that the method according to the above embodiments can be implemented by means of software plus a necessary general hardware platform. Of course, it can also be implemented by hardware, but in many cases the former is a better implementation method.

[0101] Figure 4 This is a schematic structural diagram of a storage link switching device based on an expansion card provided by an embodiment of the present application. The storage link switching device based on an expansion card provided by the embodiment of the present application is applied to a storage server. The storage server includes: a plurality of first-level expansion cards, at least one main controller, a plurality of second-level expansion cards, and a plurality of slave controllers. One first-level expansion card corresponds to a plurality of second-level expansion cards, and one second-level expansion card corresponds to one slave controller. The device is used for the main controller. As Figure 4 shown, the storage link switching device based on an expansion card provided by the embodiment of the present application includes: a judgment module 401, a link disconnection module 402, a sending module 403, a termination response module 404, a receiving module 405, a control module 406, and a switching module 407.

[0102] The judgment module 401 is configured to judge whether there is a faulty first-level expansion card during the communication process with a plurality of first-level expansion cards;

[0103] The link disconnection module 402 is configured to disconnect the integrated circuit bus link with the faulty first-level expansion card if it is determined that there is a faulty first-level expansion card;

[0104] The sending module 403 is configured to send a command to open a standby integrated circuit bus link to the non-faulty first-level expansion cards, so that the non-faulty first-level expansion cards open the standby integrated circuit bus link according to the command to open the standby integrated circuit bus link;

[0105] The termination response module 404 is configured to send a takeover request to the slave controllers of the plurality of second-level expansion cards corresponding to the faulty first-level expansion card through the standby integrated circuit bus link of the non-faulty first-level expansion card, so that the slave controllers of the plurality of second-level expansion cards corresponding to the faulty first-level expansion card terminate responding to the commands of the faulty first-level expansion card;

[0106] The receiving module 405 is configured to receive the takeover response sent by the slave controllers of the plurality of second-level expansion cards corresponding to the faulty first-level expansion card;

[0107] The control module 406 is configured to control the slave controllers of the plurality of second-level expansion cards corresponding to the faulty first-level expansion card through the main integrated circuit bus link of the non-faulty first-level expansion card according to the takeover response, and control the slave controllers of the plurality of second-level expansion cards corresponding to the non-faulty first-level expansion card;

[0108] The switching module 407 is configured to switch the storage signals of the plurality of second-level expansion cards corresponding to the faulty first-level expansion card to the standby storage link of the non-faulty first-level expansion card to complete the switching of the storage link.

[0109] In a possible implementation, the determination module 401 includes:

[0110] A first determination unit, configured to determine that there is a faulty first-level expansion card if a failure status signal actively sent by any one of the multiple first-level expansion cards is received during the communication with the multiple first-level expansion cards;

[0111] Or / and

[0112] A sending unit, configured to send commands to the multiple first-level expansion cards during the communication with the multiple first-level expansion cards, so that the multiple first-level expansion cards respond to the commands;

[0113] A second determination unit, configured to, if no response sent by any one of the first-level expansion cards is received, continuously send the commands to any one of the first-level expansion cards a preset number of times after a preset time period, and determine that there is a faulty first-level expansion card if no response sent by any one of the first-level expansion cards is received.

[0114] In a possible implementation, the storage link switching device based on the expansion card further includes: a test module, configured to perform link tests on the main integrated circuit bus link and the standby integrated circuit bus link of each first-level expansion card; wherein the link test includes a test preparation stage, a test stage, and a test end stage.

[0115] In a possible implementation, the storage server further includes: a baseboard management controller. The test module includes a test preparation unit, and the test preparation unit includes:

[0116] A first sending subunit, configured to send a control application with a link stress test request flag to each first-level expansion card, so that each first-level expansion card sends the control application with the link stress test request flag to the slave controllers of the multiple second-level expansion cards corresponding to each first-level expansion card through the main integrated circuit bus link, so that the slave controllers of the multiple second-level expansion cards corresponding to each first-level expansion card open the upstream standby integrated circuit bus link, and send a ready state signal to each first-level expansion card, so that each first-level expansion card opens the downstream standby integrated circuit bus link.

[0117] A first receiving subunit, configured to receive the ready state signals sent by each first-level expansion card.

[0118] A second sending subunit, configured to send the ready state signal to the baseboard management controller to complete the test preparation stage.

[0119] In a possible implementation, the test module includes a test unit, and the test unit includes:

[0120] A second receiving subunit, configured to receive the in-position information query command sent by the baseboard management controller;

[0121] A third sending subunit, configured to send an in-position information query command to each first-level expansion card, so that each first-level expansion card performs the following steps: according to the in-position information query command, obtain the in-position information; through the main integrated circuit bus link, send the flag bit of each first-level expansion card and the in-position information query command to the slave controllers of multiple second-level expansion cards corresponding to each first-level expansion card, so that the slave controllers of each second-level expansion card corresponding to each first-level expansion card send the in-position information of each second-level expansion card to the first-level expansion card corresponding to the flag bit through the main integrated circuit bus link; through the standby integrated circuit bus link, send the flag bit of each first-level expansion card and the temperature query command to the slave controllers of multiple second-level expansion cards corresponding to the remaining first-level expansion cards, so that the slave controllers of each second-level expansion card corresponding to the remaining first-level expansion cards send the temperature information of each second-level expansion card to the first-level expansion card corresponding to the flag bit through the standby integrated circuit bus link;

[0122] A third receiving subunit, configured to receive the in-position information of each first-level card, the in-position information of each second-level expansion card, and the temperature information of each second-level expansion card sent by each first-level expansion card.

[0123] In a possible implementation manner, the test module includes a test end unit, and the test end unit includes:

[0124] A fourth sending subunit, configured to send a stop command to each first-level expansion card after reaching a preset test time, so that each first-level expansion card stops sending the flag bit, the in-position information query command, and the temperature query command of each first-level expansion card;

[0125] A fifth sending subunit, configured to send a control application with a link stress test stop flag to each first-level expansion card, so that each first-level expansion card sends the control application with the link stress test stop flag to the slave controllers of multiple second-level expansion cards corresponding to each first-level expansion card through the main integrated circuit bus link; so that the slave controllers of multiple second-level expansion cards corresponding to each first-level expansion card close the upstream standby integrated circuit bus link and send a completion status signal to each first-level expansion card; so that each first-level expansion card closes the downstream standby integrated circuit bus link;

[0126] A fourth receiving subunit, configured to receive the completion status signal sent by each first-level expansion card;

[0127] A sixth sending subunit, configured to send the completion status signal to the baseboard management controller to complete the test end stage.

[0128] In a possible implementation manner, the storage server further includes: a host bus adapter card and multiple storage devices; one second-level expansion card corresponds to one storage device. The storage link switching device based on the expansion card further includes: a storage link test module. The storage link test module includes:

[0129] A seventh sending subunit, configured to send an open standby storage link command to each first-level expansion card, so that each first-level expansion card opens a standby storage link according to the standby storage link command;

[0130] An eighth sending subunit, configured to send a close main storage link command to each first-level expansion card, so that each first-level expansion card sends the close main storage link command to slave controllers of multiple slave second-level expansion cards corresponding to the first-level expansion card through a main integrated circuit bus link, so that the slave controllers of multiple slave second-level expansion cards corresponding to each first-level expansion card close the main storage link according to the close main storage link command;

[0131] A fifth receiving subunit, configured to receive read / write instructions sent by a host bus adapter card;

[0132] A ninth sending subunit, configured to send the read / write instructions to each first-level expansion card, so that each first-level expansion card sends the read / write instructions to slave controllers corresponding to multiple second-level expansion cards corresponding to the remaining first-level expansion cards through a standby storage link, so that the slave controllers corresponding to multiple second-level expansion cards corresponding to the remaining first-level expansion cards send the read / write instructions to corresponding storage devices, so that the storage devices perform read / write operations according to the read / write instructions, and send return values of the read / write instructions to a storage server, so that the storage server determines whether the standby storage links of each first-level expansion card are normal according to the return values.

[0133] For the description of the features in the corresponding embodiments of the storage link switching device based on expansion cards, reference can be made to the relevant descriptions in the corresponding embodiments of the storage link switching method based on expansion cards, which will not be elaborated here one by one.

[0134] Figure 5 It is a schematic structural diagram of a storage server provided in an embodiment of the present application. As Figure 5 shown, the storage server provided in this embodiment includes: at least one processor 501 and a memory 502. Optionally, the storage server further includes a communication component 503. Among them, the processor 501, the memory 502, and the communication component 503 are connected through a bus.

[0135] In a specific implementation process, at least one processor 501 executes computer execution instructions stored in the memory 502, so that at least one processor 501 executes the above-mentioned embodiment of the storage link switching method based on expansion cards.

[0136] For the specific implementation process of the processor 501, reference can be made to the above method embodiment, and its implementation principle and technical effects are similar, which will not be elaborated here in this embodiment.

[0137] In the above embodiments, it should be understood that the processor may be a central processing unit (CPU), or may also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), etc. The general-purpose processor may be a microprocessor or any conventional processor, etc. The steps of the method disclosed in combination with the application can be directly implemented by a hardware processor, or implemented by a combination of hardware and software modules in the processor.

[0138] The memory may include a random access memory (RAM), and may also include a non-volatile memory (NVM), such as at least one disk memory.

[0139] The bus may be an industry standard architecture (ISA) bus, a peripheral component interconnect (PCI) bus, an extended industry standard architecture (EISA) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For the convenience of representation, the bus in the drawings of this application is not limited to only one bus or one type of bus.

[0140] The embodiments of the present application also provide a computer-readable storage medium, in which a computer program is stored, and the computer program is configured to execute the steps in any one of the above XX method embodiments when running.

[0141] In an exemplary embodiment, the above computer-readable storage medium may include, but is not limited to: USB flash drives, read-only memories (ROMs), random access memories (RAMs), mobile hard disks, magnetic disks, or optical discs and other media that can store computer programs.

[0142] The embodiments of the present application also provide a computer program product, the above computer program product includes a computer program, and when the computer program is executed by a processor, it implements the steps in any one of the above embodiments of the storage link switching method based on an expansion card.

[0143] Embodiments of the present application further provide another computer program product, including a non-volatile computer-readable storage medium storing a computer program, where the computer program, when executed by a processor, implements the steps in any of the above embodiments of the storage link switching method based on an expansion card.

[0144] Those skilled in the art can further realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, computer software, or a combination of the two. To clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described according to functions in the above description. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present application.

[0145] The above has introduced in detail a storage link switching method, device, and storage server based on an expansion card provided by the present application. Specific examples are used herein to elaborate on the principle and implementation manner of the present application. The description of the above embodiments is only used to help understand the method and its core idea of the present application. It should be noted that for those of ordinary skill in the art in the technical field, without departing from the principle of the present application, several improvements and modifications can be made to the present application, and these improvements and modifications also fall within the protection scope of the claims of the present application.

Claims

1. A storage link switching method based on an expansion card, characterized in that: The method is applied to a storage server, the storage server comprising: a plurality of primary expansion cards, at least one master controller, a plurality of secondary expansion cards and a plurality of slave controllers, one primary expansion card corresponds to a plurality of secondary expansion cards, and one secondary expansion card corresponds to a slave controller; the method is applied to the master controller, comprising: During the communication with the plurality of primary expansion cards, determining whether there is a primary expansion card that fails; If it is determined that there is a faulty primary expansion card, disconnecting the integrated circuit bus link with the faulty primary expansion card; Sending a command to open a standby integrated circuit bus link to a primary expansion card that has not failed, so that the primary expansion card that has not failed opens the standby integrated circuit bus link according to the command to open the standby integrated circuit bus link; Sending a takeover request to the slave controllers of the multiple secondary expansion cards corresponding to the faulty primary expansion card through the spare integrated circuit bus link of the non-faulty primary expansion card, so that the slave controllers of the multiple secondary expansion cards corresponding to the faulty primary expansion card stop responding to the command of the faulty primary expansion card; Receiving takeover responses sent from a controller of a plurality of secondary expansion cards corresponding to the faulty primary expansion card; According to the takeover response, the slave controllers of the multiple secondary expansion cards corresponding to the failed primary expansion card are controlled through the spare integrated circuit bus link of the surviving primary expansion card, and the slave controllers of the multiple secondary expansion cards corresponding to the surviving primary expansion card are controlled through the main integrated circuit bus link of the surviving primary expansion card; The storage signals of the multiple secondary expansion cards corresponding to the faulty primary expansion card are switched to the backup storage link of the primary expansion card that has not failed, so as to complete the switching of the storage link.

2. The method according to claim 1, characterized in that In the process of communicating with the plurality of primary expansion cards, determining whether there is a primary expansion card that fails includes: During the communication process with the plurality of primary expansion cards, if a failure status signal actively sent by any primary expansion card is received, it is determined that there is a primary expansion card that has a fault; or / and During the communication process with the plurality of primary expansion cards, sending commands to the plurality of primary expansion cards so that the plurality of primary expansion cards respond to the commands; If no response is received from any primary expansion card, a preset number of commands are continuously sent to any primary expansion card after a preset time period. If no response is received from any primary expansion card, it is determined that a faulty primary expansion card exists.

3. The method according to claim 1, characterized in that The method further comprises: before determining whether there is a faulty primary expansion card during the communication process with the plurality of primary expansion cards: A link test is performed on the main integrated circuit bus link and the standby integrated circuit bus link of each first-level expansion card; wherein the link test includes a test preparation phase, a test phase and a test end phase.

4. The method according to claim 3, characterized in that The storage server further includes: a baseboard management controller; The test preparation stage includes: Sending a control application with a link stress test request flag to each first-level expansion card, so that each first-level expansion card sends a control application with a link stress test request flag to the slave controllers of multiple second-level expansion cards corresponding to each first-level expansion card through the main integrated circuit bus link, so that the slave controllers of multiple second-level expansion cards corresponding to each first-level expansion card open an uplink standby integrated circuit bus link, and sending a ready state signal to each first-level expansion card, so that each first-level expansion card opens a downlink standby integrated circuit bus link; Receiving the ready state signal sent by each primary expansion card; The ready status signal is sent to the baseboard management controller to complete the test preparation phase.

5. The method according to claim 4, characterized in that The testing phase includes: Receiving a presence information query command sent by the baseboard management controller; The in-place information query command is sent to each first-level expansion card, so that each first-level expansion card performs the following steps: obtaining in-place information according to the in-place information query command; sending the flag bit of each first-level expansion card and the in-place information query command to the slave controllers of multiple second-level expansion cards corresponding to each first-level expansion card through the main integrated circuit bus link, so that the slave controllers of each second-level expansion card corresponding to each first-level expansion card send the in-place information of each second-level expansion card to the first-level expansion card corresponding to the flag bit through the main integrated circuit bus link; sending the flag bit of each first-level expansion card and the temperature query command to the slave controllers of multiple second-level expansion cards corresponding to the remaining first-level expansion cards through the spare integrated circuit bus link, so that the slave controllers of each second-level expansion card corresponding to the remaining first-level expansion card send the temperature information of each second-level expansion card to the first-level expansion card corresponding to the flag bit through the spare integrated circuit bus link; The presence information of each primary card, the presence information of each secondary expansion card, and the temperature information of each secondary expansion card sent by each primary expansion card are received.

6. The method according to claim 5, characterized in that The test end stage includes: After the preset test time is reached, a stop command is sent to each first-level expansion card, so that each first-level expansion card stops sending the flag bit of each first-level expansion card, the in-place information query command and the temperature query command; Sending a control application with a link stress test stop flag to each of the first-level expansion cards, so that each of the first-level expansion cards sends the control application with the link stress test stop flag to the slave controllers of the multiple second-level expansion cards corresponding to each of the first-level expansion cards through the main integrated circuit bus link; so that the slave controllers of the multiple second-level expansion cards corresponding to each of the first-level expansion cards close the uplink standby integrated circuit bus link, and send a completion status signal to each of the first-level expansion cards; so that each of the first-level expansion cards closes the downlink standby integrated circuit bus link; Receiving the completion status signal sent by each primary expansion card; The completion status signal is sent to the baseboard management controller to complete the test end phase.

7. The method according to claim 3, characterized in that The storage server further comprises: a host bus adapter card and a plurality of storage devices; one of the secondary expansion cards corresponds to one storage device; After the link test is performed on the main integrated circuit bus link and the standby integrated circuit bus link of each primary expansion card, the method further includes: Sending a standby storage link opening command to each of the first-level expansion cards, so that each of the first-level expansion cards opens the standby storage link according to the standby storage link command; Sending a main storage link closing command to each of the first-level expansion cards, so that each of the first-level expansion cards sends the main storage link closing command to the slave controllers of the multiple slave second-level expansion cards corresponding to each of the first-level expansion cards through the main integrated circuit bus link, so that the slave controllers of the multiple slave second-level expansion cards corresponding to each of the first-level expansion cards close the main storage link according to the main storage link closing command; receiving a read / write instruction sent by the host bus adapter card; The read / write instructions are sent to each first-level expansion card so that each first-level expansion card sends the read / write instructions to the slave controllers corresponding to the multiple second-level expansion cards corresponding to the remaining first-level expansion cards through the backup storage link, so that the slave controllers corresponding to the multiple second-level expansion cards corresponding to the remaining first-level expansion cards send the read / write instructions to the corresponding storage device so that the storage device performs read / write operations according to the read / write instructions, and the return value of the read / write instruction is sent to the storage server so that the storage server determines whether the backup storage link of each first-level expansion card is normal according to the return value.

8. A storage link switching device based on an expansion card, characterized in that: Applied to a storage server, the storage server includes: multiple primary expansion cards, at least one main controller, multiple secondary expansion cards and multiple slave controllers, one primary expansion card corresponds to multiple secondary expansion cards, and one secondary expansion card corresponds to one slave controller; the device is used for the main controller, including: A judgment module, used for judging whether there is a faulty primary expansion card during the communication process with the plurality of primary expansion cards; A link disconnection module, used for disconnecting the integrated circuit bus link with the faulty primary expansion card if it is determined that there is a faulty primary expansion card; a sending module, used for sending a command to open a standby integrated circuit bus link to a primary expansion card that has not failed, so that the primary expansion card that has not failed opens the standby integrated circuit bus link according to the command to open the standby integrated circuit bus link; A termination response module, used for sending a takeover request to the slave controllers of the multiple secondary expansion cards corresponding to the faulty primary expansion card through the spare integrated circuit bus link of the non-faulty primary expansion card, so that the slave controllers of the multiple secondary expansion cards corresponding to the faulty primary expansion card stop responding to the command of the faulty primary expansion card; A receiving module, used for receiving takeover responses sent from the controller of multiple secondary expansion cards corresponding to the faulty primary expansion card; a control module, configured to control the slave controllers of the plurality of secondary expansion cards corresponding to the failed primary expansion card through the standby integrated circuit bus link of the primary expansion card that has not failed according to the takeover response, and control the slave controllers of the plurality of secondary expansion cards corresponding to the failed primary expansion card through the main integrated circuit bus link of the failed primary expansion card; The switching module is used to switch the storage signals of multiple secondary expansion cards corresponding to the faulty primary expansion card to the backup storage link of the primary expansion card that has not failed, so as to complete the switching of the storage link.

9. A storage server, characterized in that: include: Memory for storing computer programs; A processor, configured to implement the steps of the storage link switching method based on the expansion card as described in any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, wherein the computer program, when executed by a processor, implements the steps of the storage link switching method based on an expansion card as claimed in any one of claims 1 to 7.

Images