Hot plug management system and method for a server storage device

Abstract

The application relates to the technical field of server storage devices, in particular to a hot plug control system and method for a server storage device, which acquires connection state detection information in the process of plugging in and unplugging the server storage device, the connection state detection information comprising a first detection contact state, a second detection contact state, a power connection state and time parameters corresponding to changes in the states, which are set at a storage device interface; the hot plug stage currently reached by the storage device is determined according to the change sequence of the first detection contact state and the second detection contact state, and a connection stability evaluation value is calculated according to the state change time interval determined by the time parameters between different detection contacts; whether the storage device reaches a safe connection state is judged according to the connection stability evaluation value. The application reduces the risk of data loss and equipment damage, thereby improving the safety, reliability and operation stability of the hot plug process of the server storage device.

Description

Technical Field

[0001] This invention relates to a hot-swap control system and method for server storage devices, belonging to the technical field of server storage devices. Background Technology

[0002] As server data processing capabilities and storage capacity requirements continue to increase, servers typically adopt a hot-swappable storage device architecture, enabling storage hard drives to be inserted, removed, or replaced during server operation.

[0003] Existing hot-swappable solutions for server storage devices typically determine whether a storage device is connected by setting a device presence detection signal (such as inserting a detection pin). Once a device connection is detected, power is directly turned on and data communication is established. When a device is removed, data link shutdown and power cut-off operations are performed based on changes in the detection signal.

[0004] However, existing hot-swapping methods mainly rely on the state of the device after it has been inserted or removed, and cannot detect the dynamic process of the connector contacts gradually making or breaking contact during the insertion or removal of the storage device. When there are situations such as improper insertion, changes in contact resistance, power establishment delay, or unstable communication links, it can easily lead to abnormal identification of the storage device, interruption of data transmission, or even damage to the device, reducing the reliability of the server storage system. Therefore, there is an urgent need to improve a hot-swapping control system and method for server storage devices to solve the above-mentioned problems. Summary of the Invention

[0005] The purpose of this invention is to provide a hot-swappable management system and method for server storage devices. By setting up multi-level state detection contacts with different contact timings, the system acquires contact change information during the insertion or removal of the storage device. Combined with power supply status and data link status, the system predicts and judges the current connection status of the storage device. Power supply and communication establishment operations are only performed after confirming that safe connection conditions have been met. Data protection and power-off operations are performed in advance when the device is predicted to be disconnected. This avoids data loss, communication abnormalities, and storage device damage caused by unstable status during the insertion and removal process, thereby improving the safety and reliability of the hot-swappable process of server storage devices.

[0006] To achieve the above objectives, the present invention provides the following technical solution:

[0007] A hot-swap control system and method for server storage devices, comprising the following steps:

[0008] The system acquires connection status detection information during the insertion and removal of server storage devices. This information includes the status of a first detection contact, a second detection contact, a power connection status, and time parameters corresponding to changes in each status, all located at the storage device interface. Based on the order of changes in the first and second detection contact states, the system determines the current hot-plug stage of the storage device and calculates a connection stability evaluation value based on the time intervals between state changes determined by the time parameters between different detection contacts. The system then determines whether the storage device has reached a safe connection state based on the connection stability evaluation value. When a safe connection state is determined, the system controls the server power module to output operating power to the storage device and controls the data link module to establish a data communication connection between the storage device and the server main controller. When the storage device is detected to be in a removed state, the system predicts the disconnection trend of the storage device based on the disconnection order of the first and second detection contacts and controls the data link module to stop data transmission and the power module to perform a power-off operation before the storage device is completely disconnected.

[0009] Furthermore, the storage device interface is provided with at least two status detection contacts, and the length of the first detection contact is greater than the length of the second detection contact. The length of the second detection contact is greater than the length of the power contact and the data communication contact. During the insertion of the storage device, the first detection contact first contacts the server backplane, and the second detection contact then establishes a connection to form a multi-stage status detection process with a time difference.

[0010] Furthermore, calculating the connection stability evaluation value based on the connection status detection information includes obtaining the first time parameter for establishing a connection at the first detection contact, the second time parameter for establishing a connection at the second detection contact, the power supply voltage stabilization time parameter, and the data link establishment time parameter.

[0011] The connection stability evaluation value is obtained by weighting the calculations based on each time parameter. Connection stability evaluation value The mathematical expression is: ;

[0012] In the formula, Indicates the connection establishment time of the first detection contact. Indicates the connection establishment time of the second detection contact. Indicates the power supply output settling time. Indicates the data link establishment time. This indicates the weight of the corresponding parameter.

[0013] Furthermore, a secure connection threshold is preset;

[0014] When the connection stability value is greater than or equal to the security threshold, it is determined that the storage device has reached a secure access state;

[0015] When the connection stability evaluation value is less than the secure connection threshold, the data link module remains in an isolated state and continues to collect storage device connection status detection information.

[0016] Furthermore, during the insertion of the storage device, a phased power supply method is used to control the power supply to the storage device;

[0017] In the first stage, the detection power supply is turned on according to the state of the first detection contact.

[0018] In the second stage, the changes in power supply voltage and current are detected based on the state of the second detection contact.

[0019] In the third stage, the main power supply is turned on after the connection stability evaluation value meets the requirements.

[0020] Furthermore, the data link module is kept disconnected until the storage device reaches a secure connection state. When the power output is detected to be stable and the data link status meets the communication conditions, the data link module is turned on to prevent the storage device from accessing data under unstable power conditions.

[0021] Furthermore, during the process of removing the storage device, the disconnection status of the first detection contact and the second detection contact is detected in real time. When it is detected that the second detection contact is disconnected first and the first detection contact is still in the connected state, it is determined that the storage device has entered the pre-disconnection state, and data protection operations are performed in advance according to the pre-disconnection state.

[0022] Furthermore, the data protection operations include stopping the sending of new data write requests to the storage device, controlling the server main controller to perform cache data refresh operations, saving the current storage device operating status information, and closing the storage device data communication channel.

[0023] Furthermore, the predicted storage device disconnection trend includes calculating a disconnection stability evaluation value based on the contact disconnection time during the unplugging process. Disconnect stable evaluation value The mathematical expression is: ;

[0024] In the formula, Indicates the time it takes for the first detection contact to disconnect. Indicates the time when the second detection contact is disconnected. This indicates the change in the operating current of the storage device. This indicates the corresponding parameter weight. When the disconnection stability evaluation value reaches the preset disconnection condition, the control power module cuts off the working power of the storage device.

[0025] Furthermore, it includes a status detection module for collecting the status of detection contacts, power supply status, and data link status during the insertion or removal of the storage device.

[0026] A stability judgment module, connected to the state detection module, is used to calculate the connection stability evaluation value and the disconnection stability evaluation value based on the state change relationship between the detection contacts.

[0027] A hot-swap control module, connected to the stability judgment module, is used to control the power module and data link module to perform phased access or disconnection operations based on the stability judgment result.

[0028] The data protection module is used to perform data write stop, cache refresh, and communication isolation operations on the storage device when it is detected that the storage device has entered a pre-disconnect state.

[0029] Compared with the prior art, the beneficial effects of the present invention are:

[0030] This invention, by setting multi-level state detection contacts with different contact timings at the server storage device interface, acquires real-time state change information during the insertion or removal of the storage device. Based on contact change time, power establishment status, and data link status, it predicts and judges the connection stability of the storage device, realizing a shift from traditional "state detection followed by response" to "state prediction followed by control." During storage device insertion, phased power supply and delayed data communication connection establishment avoid device recognition failure due to unstable contact or abnormal power supply. During storage device removal, by identifying disconnection trends in advance and executing data write stop, cache refresh, and safe power-off operations, it reduces the risk of data loss and device damage, thereby improving the safety, reliability, and operational stability of the server storage device hot-swapping process. Attached Figure Description

[0031] Figure 1 This is a flowchart of a hot-plug management method for server storage devices according to the present invention. Detailed Implementation

[0032] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0033] This embodiment provides a hot-swap control system for server storage devices, including a server main control module, a storage backplane module, a multi-level status detection module, a status detection module, a stability judgment module, a hot-swap control module, and a data protection module.

[0034] The server main control module is used to perform storage device management tasks, including storage device identification, data access control, buffer management and file system unloading control. The server main control module can be a server processor, a baseboard management controller or a storage controller.

[0035] The storage backplane module is located inside the server chassis and is used to connect multiple storage devices. The storage backplane module includes storage device slots, power connection interfaces, data communication interfaces, and status detection interfaces.

[0036] The status detection interface is equipped with multiple levels of detection contacts to acquire status changes during the insertion or removal of the storage device.

[0037] The multi-level status detection module includes a first detection contact, a second detection contact, a power detection contact, and a data link detection contact;

[0038] The first detection contact is located at the front end of the interface and has the longest length. During the insertion of the storage device, the first detection contact is the first to make contact. During the removal process, the first detection contact is the last to disconnect. This is used to obtain the initial entry state of the storage device.

[0039] The second detection contact is shorter than the first detection contact, and its contact time is between that of the first detection contact and the power contact, which is used to further determine the stability of the mechanical connection.

[0040] The power detection contact is used to detect whether the power supply is established, whether the output voltage is stable, and whether the operating current is normal.

[0041] Data link detection contacts are used to detect the establishment status of data communication channels and the stability of data transmission.

[0042] And through the above-mentioned multi-level detection contacts, the insertion process is formed as follows: the first detection contact is turned on, the second detection contact is turned on, power is established, and data link is established.

[0043] And the process of pulling out the device, which involves the formation of changes in the first detection contact, changes in the second detection contact, data isolation, and power-off;

[0044] The status detection module is used to collect the status of detection contacts, power status, and data link status during the insertion or removal of storage devices.

[0045] A stability judgment module, connected to the state detection module, is used to calculate the connection stability evaluation value and the disconnection stability evaluation value based on the state change relationship between the detection contacts.

[0046] A hot-swap control module, connected to the stability judgment module, is used to control the power module and data link module to perform phased access or disconnection operations based on the stability judgment result.

[0047] The data protection module is used to perform data write stop, cache refresh, and communication isolation operations on the storage device when it is detected that the storage device has entered a pre-disconnect state.

[0048] like Figure 1 As shown in this embodiment, the principle of a hot-swappable control method for server storage devices is as follows:

[0049] Step 1: Collect storage device insertion / removal status information: When the user inserts the storage device into the server storage slot, the status detection module collects the first detection contact connection signal, the second detection contact connection signal, the power output status, and the data communication status in real time, and records the time of each status occurrence at the same time;

[0050] In one possible embodiment, the establishment time of the first detection contact is... The time for establishing the second detection contact is The power supply stabilization time is The data link establishment time is ;

[0051] Specifically, Indicates the time when the storage device initially enters the interface. This indicates the time it takes for the mechanical connection to further stabilize. This indicates the time it takes for the power supply to reach a stable state. Indicates the time required for data communication preparation to complete;

[0052] Step 2: Determine the storage device insertion stage: The status detection module determines the current insertion stage based on the sequence of changes in the detection contacts, specifically including:

[0053] When only the first detection contact is detected to be connected: it is determined that the storage device is in the initial insertion state;

[0054] When the second detection contact is detected to be closed: it is determined that the storage device has entered a mechanically stable connection state;

[0055] When normal power contacts are detected: the storage device is determined to have entered the power-on phase.

[0056] When the data link is normal: it is determined that the storage device has entered the communication preparation stage. The above method avoids the problem of directly powering on and communicating with the device as soon as it is plugged in, which is a problem in the traditional method.

[0057] Step 3: Calculate the connection stability evaluation value: Calculate the storage device connection stability evaluation value based on the collected time parameters. ;

[0058] In the formula, Indicates the connection establishment time of the first detection contact. Indicates the connection establishment time of the second detection contact. Indicates the power supply output settling time. Indicates the data link establishment time. This indicates the weight of the corresponding parameter, and , The timer is obtained from the internal timing of the status detection module. The time it takes for the voltage to reach a stable threshold is obtained by the power supply detection circuit. The time is obtained by detecting the link training completion time using the communication control module.

[0059] Step 4: Implement phased power supply control: When the storage device is inserted, do not immediately turn on all operating power. The specific process is as follows:

[0060] Phase 1: Turn on the low-power detection power supply to detect the interface connection status and device identification information;

[0061] Phase Two: Detect the power supply output voltage, operating current, and current variation trend; determine if any issues exist.

[0062] Transient impacts and abnormal contact situations;

[0063] Phase Three: When ( When the preset safe connection threshold is reached, the main power supply is turned on to reduce the current surge generated during plugging and unplugging.

[0064] Step 5: Establish data communication connection: After the main power supply is stable, the hot-swap control module controls the data link switch to close;

[0065] Establish data communication between storage devices, storage controllers, and the server main control module;

[0066] like ( If the preset secure connection threshold is used, the data link will remain closed;

[0067] Avoid data transmission when the power supply is unstable, the contact resistance is abnormal, or the signal quality is insufficient.

[0068] Step 6: Detect storage device removal trend: When the user removes the detection module, the status detection module detects the status of the first detection contact, the status of the second detection contact, and the current change status in real time.

[0069] Because the first and second detection contacts have different lengths, a time advance will occur during the pulling process;

[0070] The time of change of the first detection contact point was recorded as follows: The time of change of the second detection contact is recorded as follows ;

[0071] Step 7: Calculate the disconnection trend evaluation value: Calculated based on the status of the pull-out process. ;

[0072] In the formula, Indicates the time it takes for the first detection contact to disconnect. Indicates the time when the second detection contact is disconnected. This indicates the change in the operating current of the storage device. Indicates the weight of the corresponding parameter;

[0073] in, , The time is obtained by the status detection module. Obtained by the current sampling module;

[0074] Step 8: Perform data protection operations: When it is determined that the storage device has entered a pre-disconnect state:

[0075] The server's main control module performs the following actions: stops new data write requests, completes cache data refresh, saves the storage device's operating status, and shuts down the data communication link. During this time, the storage device continues to be powered.

[0076] Compared to the traditional direct power outage method, it provides time for data migration and cache preservation;

[0077] Step 9: Perform a safety power disconnection:

[0078] when ( When the preset disconnection threshold is reached, the hot-plug control module executes the action of shutting down the data link.

[0079] Turn off the power supply and disconnect the interface to complete the safe hot-pull-out process.

[0080] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the invention can be implemented in other specific forms without departing from its spirit or essential characteristics. Therefore, the embodiments should be considered in all respects as exemplary and non-limiting, and the scope of the invention is defined by the appended claims rather than the foregoing description. Thus, all variations falling within the meaning and scope of equivalents of the claims are intended to be included within the present invention. No reference numerals in the claims should be construed as limiting the scope of the claims.

[0081] Furthermore, it should be understood that although this specification describes embodiments, not every embodiment contains only one independent technical solution. This narrative style is merely for clarity. Those skilled in the art should consider the specification as a whole, and the technical solutions in each embodiment can also be appropriately combined to form other embodiments that can be understood by those skilled in the art.

Claims

1. A method for controlling the hot-swapping of server storage devices, characterized in that, Includes the following steps: The connection status detection information during the insertion and removal of the server storage device is obtained. The connection status detection information includes the status of the first detection contact, the status of the second detection contact, the power connection status, and the time parameters corresponding to the changes in each status, all set at the storage device interface. Based on the sequence of changes in the states of the first and second detection contacts, the current hot-plug stage of the storage device is determined, and the connection stability evaluation value is calculated based on the time interval of state changes determined by the time parameters between different detection contacts. Determine whether the storage device has reached a secure connection state based on the connection stability evaluation value; When it is determined that the storage device has reached a secure connection state, the control server power module outputs operating power to the storage device and controls the data link module to establish a data communication connection between the storage device and the server main controller. When the storage device is detected to be in a disconnected state, the disconnection trend of the storage device is predicted according to the disconnection sequence of the first detection contact and the second detection contact, and the data link module is controlled to stop data transmission and the power module is controlled to perform a power-off operation before the storage device is completely disconnected.

2. The hot-swappable control method for server storage devices according to claim 1, characterized in that: The storage device interface is provided with at least two status detection contacts, and the length of the first detection contact is greater than the length of the second detection contact. The length of the second detection contact is greater than the length of the power contact and the data communication contact. During the insertion of the storage device, the first detection contact first contacts the server backplane, and the second detection contact then establishes a connection to form a multi-stage status detection process with a time difference.

3. The hot-swappable control method for server storage devices according to claim 1, characterized in that: The connection stability evaluation value is calculated based on the connection status detection information, including obtaining the first time parameter for establishing a connection at the first detection contact, the second time parameter for establishing a connection at the second detection contact, the power supply voltage stabilization time parameter, and the data link establishment time parameter. The connection stability evaluation value is obtained by weighting the calculations based on each time parameter. Connection stability evaluation value The mathematical expression is: ; In the formula, Indicates the connection establishment time of the first detection contact. Indicates the connection establishment time of the second detection contact. Indicates the power supply output settling time. Indicates the data link establishment time. This indicates the weight of the corresponding parameter.

4. The hot-swappable control method for server storage devices according to claim 3, characterized in that: Pre-set secure connection thresholds; When the connection stability value is greater than or equal to the security threshold, it is determined that the storage device has reached a secure access state; When the connection stability evaluation value is less than the secure connection threshold, the data link module remains in an isolated state and continues to collect storage device connection status detection information.

5. The hot-swappable control method for server storage devices according to claim 1, characterized in that: During the insertion of the storage device, a phased power supply method is used to control the power supply to the storage device; In the first stage, the detection power supply is turned on according to the state of the first detection contact. In the second stage, the changes in power supply voltage and current are detected based on the state of the second detection contact. In the third stage, the main power supply is turned on after the connection stability evaluation value meets the requirements.

6. The hot-swappable control method for server storage devices according to claim 1, characterized in that: The control data link module remains disconnected until the storage device reaches a secure connection state. When the power output is detected to be stable and the data link status meets the communication conditions, the control data link module is turned on to prevent the storage device from accessing data when the power supply is unstable.

7. The hot-swappable control method for server storage devices according to claim 2, characterized in that: During the removal of the storage device, the disconnection status of the first and second detection contacts is monitored in real time. When the second detection contact is detected to be disconnected first while the first detection contact is still connected, it is determined that the storage device has entered a pre-disconnection state, and data protection operations are performed in advance based on the pre-disconnection state.

8. The hot-swappable control method for a server storage device according to claim 7, characterized in that: The data protection operations include stopping the sending of new data write requests to the storage device, controlling the server main controller to perform cache data refresh operations, saving the current operating status information of the storage device, and closing the data communication channel of the storage device.

9. The hot-swappable control method for a server storage device according to claim 7, characterized in that: The predicted storage device disconnection trend includes calculating a disconnection stability evaluation value based on the contact disconnection time during the removal process. Disconnect stable evaluation value The mathematical expression is: ; In the formula, Indicates the time it takes for the first detection contact to disconnect. Indicates the time when the second detection contact is disconnected. This indicates the change in the operating current of the storage device. This indicates the corresponding parameter weight. When the disconnection stability evaluation value reaches the preset disconnection condition, the control power module cuts off the working power of the storage device.

10. A hot-swappable control system for server storage devices, characterized in that: Includes a status detection module, used to collect the status of detection contacts, power status, and data link status during the insertion or removal of storage devices; A stability judgment module, connected to the state detection module, is used to calculate the connection stability evaluation value and the disconnection stability evaluation value based on the state change relationship between the detection contacts. A hot-swap control module, connected to the stability judgment module, is used to control the power module and data link module to perform phased access or disconnection operations based on the stability judgment result. The data protection module is used to perform data write stop, cache refresh, and communication isolation operations on the storage device when it is detected that the storage device has entered a pre-disconnect state.

Images