CN113419980A

CN113419980A - Out-of-band management method, device, controller, system and storage medium

Info

Publication number: CN113419980A
Application number: CN202110113186.1A
Authority: CN
Inventors: 吕涛; 黄子龙; 李志超
Original assignee: Alibaba Group Holding Ltd
Current assignee: Alibaba Group Holding Ltd
Priority date: 2021-01-27
Filing date: 2021-01-27
Publication date: 2021-09-21

Abstract

The embodiment of the invention provides an out-of-band management method, an out-of-band management device, a controller, a system and a storage medium. The out-of-band management method comprises the following steps: determining a current channel state of a first out-of-band management channel of an out-of-band management transport protocol, wherein the first out-of-band management channel is used for out-of-band management of a target peripheral via a processor; and if the current channel state of the first out-of-band management channel indicates that the first out-of-band channel is failed currently, switching to a second out-of-band management channel of the out-of-band management transmission protocol, and directly performing out-of-band management on the target peripheral. The scheme of the embodiment of the invention avoids the condition of interruption or stop of the management of the peripheral when the first out-of-band channel fails, thereby realizing more reliable out-of-band management.

Description

Out-of-band management method, device, controller, system and storage medium

Technical Field

The embodiment of the invention relates to the technical field of computers, in particular to an out-of-band management method, device, controller, system and storage medium.

Background

With the increasing demand of cloud computing services, the types and the number of peripheral devices in a data center server are increasing. Especially for bare metal servers, the peripherals mostly exist in the form of external board cards and are configured to communicate with the processor and memory in the server, thereby improving the computing performance of the server while providing resource isolation advantages such as secure hosting, non-virtualized application deployment, and the like.

However, for the current data center server, the reliability of peripheral management is poor, which results in higher management and control cost and operation and maintenance cost of the system.

Disclosure of Invention

Embodiments of the present invention provide an out-of-band management method, apparatus, controller, system, and storage medium to solve or alleviate the above problems.

According to a first aspect of embodiments of the present invention, there is provided an out-of-band management method, including: determining a current channel state of a first out-of-band management channel of an out-of-band management transport protocol, wherein the first out-of-band management channel is used for out-of-band management of a target peripheral via a processor; and if the current channel state of the first out-of-band management channel indicates that the first out-of-band channel is failed currently, switching to a second out-of-band management channel of the out-of-band management transmission protocol, and directly performing out-of-band management on the target peripheral.

According to a second aspect of embodiments of the present invention, there is provided an out-of-band management device, including: the device comprises a determining module, a judging module and a judging module, wherein the determining module is used for determining the current channel state of a first out-of-band management channel of an out-of-band management transmission protocol, and the first out-of-band management channel is used for carrying out-of-band management on a target peripheral through a processor; and the management module is used for switching to a second out-of-band management channel of the out-of-band management transmission protocol to directly perform out-of-band management on the target peripheral equipment if the current channel state of the first out-of-band management channel indicates that the first out-of-band channel is failed currently.

According to a third aspect of embodiments of the present invention, there is provided a management controller comprising: bus interface, communication interface and switching circuit. The communication interface is to determine a current channel state of a first out-of-band management channel of an out-of-band management transport protocol. The first out-of-band management channel is to manage a target peripheral out-of-band via a processor. If the current channel state of the first out-of-band management channel indicates that the first out-of-band channel is currently failed, the switching circuit is configured to switch to a second out-of-band management channel of the out-of-band management transmission protocol, and the bus interface is configured to directly perform out-of-band management on the target peripheral.

According to a fourth aspect of the embodiments of the present invention, there is provided a management system including: a management controller and a processor according to the third aspect.

According to a fifth aspect of embodiments of the present invention, there is provided a storage medium having stored thereon a computer program which, when executed by control circuitry, implements the method as described in the first aspect.

In the scheme of the embodiment of the invention, when the first out-of-band channel fails currently, the second out-of-band management channel of the out-of-band management transmission protocol can be switched to, and the out-of-band management is directly carried out on the target peripheral, so that the condition that the management of the peripheral is interrupted or stopped when the first out-of-band channel fails is avoided, and more reliable out-of-band management is realized.

Drawings

In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments described in the embodiments of the present invention, and it is also possible for a person skilled in the art to obtain other drawings based on the drawings.

FIG. 1 is a schematic block diagram of a typical peripheral out-of-band management system;

FIG. 2 is a schematic flow chart diagram of an out-of-band management method of another embodiment of the present invention;

FIG. 3 is a diagram illustrating an out-of-band management method according to another embodiment of the present invention;

FIG. 4 is a diagram illustrating an out-of-band management method according to another embodiment of the present invention;

FIG. 5A is a schematic flow chart diagram of an out-of-band management method according to another embodiment of the present invention;

FIG. 5B is a schematic flow chart diagram of an out-of-band management method according to another embodiment of the present invention;

FIG. 6 is a schematic block diagram of an out-of-band management apparatus of another embodiment of the present invention;

FIG. 7 is a schematic block diagram of a management controller for out-of-band management according to another embodiment of the present invention;

fig. 8 is a schematic configuration diagram of a management system for out-of-band management according to another embodiment of the present invention.

Detailed Description

In order to make those skilled in the art better understand the technical solutions in the embodiments of the present invention, the technical solutions in the embodiments of the present invention will be described clearly and completely with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all embodiments. All other embodiments obtained by a person skilled in the art based on the embodiments of the present invention shall fall within the scope of the protection of the embodiments of the present invention.

The following further describes specific implementation of the embodiments of the present invention with reference to the drawings. FIG. 1 is a schematic block diagram of a typical peripheral out-of-band management system. As shown, the peripheral out-of-band management system is configured in a specific server, and includes a processor 110, a Root Complex (RC) 120, a management controller 130, and a plurality of peripherals 140, where the server may be disposed in a computer room, for example, may be a bare metal server, or may be a physical server or other virtual server. Processor 110 may be a Central Processing Unit (CPU), for example, and may include a PCIe management engine, which may be implemented as a circuit or a module. The root complex 120 device connects the processor and memory subsystem to a PCIe switch fabric composed of one or more switch devices. The RC may have a connection topology as shown. The PCIe management engine may communicate with port 4 of the RC. The peripheral device 140 may be any component other than a processor and a memory, and the peripheral device 140 may be mounted in the form of an external board card, or may be mounted in other forms. Each peripheral 140 communicates with a respective RC port, e.g., peripheral 1, peripheral 2, and peripheral 3 communicate with port 1, port 2, and port 3, respectively. Port 4 of the RC may also communicate with the PCIe interface of the management controller 130.

Specifically, when an operation such as a restart is performed on the processor 110, the PCIe management engine may interrupt communication with the port 4 of the RC, and at the same time, the management controller 130 cannot communicate with the port 4 through the PCIe interface, and thus cannot perform reliable out-of-band management.

Fig. 2 is a schematic diagram of an out-of-band management method according to an embodiment of the present invention. The out-of-band management method of fig. 1 may be performed by a management controller. Management controllers include, but are not limited to, Baseband Management Controllers (BMCs). The method comprises the following steps:

210: determining a current channel state of a first out-of-band management channel of an out-of-band management transport protocol, wherein the first out-of-band management channel is used for out-of-band management of a target peripheral via a processor.

It should be understood that out-of-band Management Transport protocols include, but are not limited to, Management Component Transport Protocol (MCTP). In addition, the out-of-band management transport protocol may be adapted to a variety of physical layer configurations. The first out-of-band management channel may be a first bus based physical layer management channel. The first bus includes, but is not limited to, a Peripheral Component Interconnect Express (PCIe) bus. PCIe is a high-speed serial computer expansion bus standard. For example, the messages of the first bus may be PCIe Vendor custom messages (VDMs).

It should also be understood that the target peripheral may be one or more peripherals. The Processor described herein may be a general-purpose Processor, and includes a Central Processing Unit (CPU), a Network Processor (NP), and the like; but may also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an off-the-shelf programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic, discrete hardware components.

It should also be understood that the first out-of-band management channel may be utilized for out-of-band management via a switch fabric such as a Root Complex (RC), as well as management channels of other switch fabrics. For example, a first out-of-band management channel may communicate with a target peripheral via an RC port, enabling out-of-band management. Furthermore, the implementation of the functionality of the switching fabric described above is dependent on the particular operating state of the processor. For example, in a state of the processor such as an abnormal operation state or a power saving operation state, the function of the switch fabric is limited so that out-of-band management cannot be performed based on the switch fabric.

It should also be understood that the processor may also be managed out-of-band through structures other than a switch fabric such as an RC. For example, an out-of-band management agent module is included in the processor via which the out-of-band management controller manages the target peripheral out-of-band. For another example, the out-of-band management controller obtains operating status information of the processor from the processor, and performs out-of-band management on the target peripheral device based on the operating status information.

In addition, the first out-of-band management channel and the second out-of-band management channel may be based on the same protocol framework, e.g., the first out-of-band management channel and the second out-of-band management channel are different physical layer channels based on the same transport layer protocol. The first out-of-band management channel and the second out-of-band management channel may also be based on different protocol frameworks, e.g., the first out-of-band management channel and the second out-of-band management channel are based on different transport layer protocol frameworks.

220: and if the current channel state of the first out-of-band management channel indicates that the first out-of-band channel is failed currently, switching to a second out-of-band management channel of the out-of-band management transmission protocol, and directly performing out-of-band management on the target peripheral.

It should be appreciated that the second out-of-band management channel may be a second bus based physical layer management channel. The second Bus includes, but is not limited to, a System Management Bus (SMBUS) or an Inter-Integrated Circuit Bus (I2C). Direct out-of-band management of the target peripheral may refer to out-of-band management without going through a switch fabric having the above-described associations with the processor. For example, the management controller may communicate with the target peripheral device using a second bus-based interface. For example, the management controller communicates with the second bus interfaces of the plurality of peripherals, respectively. And under the normal running state of the processor, the processor and the target peripheral perform data transmission based on the first bus interface. For example, a target peripheral device is suspended below the switch fabric, and the processor is in data communication with the target peripheral device through the switch fabric.

Further, the first bus based channel may be a high speed channel, relatively speaking, for example, a high speed serial bus channel. The second bus based channel may be a low speed channel, for example, a simple pervasive channel such as a low speed serial bus channel.

It should also be appreciated that switching from the first out-of-band management channel to the second out-of-band management channel may be accomplished by a switching module of the management controller, which may appear as a switching circuit or a switching virtual unit. The function of the switching module may be independent of the function of the encapsulation module of the management controller, or the encapsulation module may be configured to have the switching function. For example, the management controller may obtain operating state information of the processor and send the operating state information to the encapsulation module, which may be in a conventional encapsulation mode above the transport layer. After the encapsulation process (the encapsulation process is only an example, and may also be a decapsulation process, which is not described in detail herein) is performed to the transport layer, physical layer encapsulation based on the outband management transport protocol may be performed according to the operation state information.

In other words, the particular switch fabric on which the first bus-based communication depends is limited by the operating state of the processor, whereas the second bus-based communication has a poor communication performance and a poor reliability of the communication quality compared to the first bus-based communication. Specifically, the solution of the embodiment of the present invention realizes a method for coexistence of two MCTP channels on the same peripheral, so that the MCTP management message transmission between the management controller and the peripheral can utilize a high-speed channel based on the first bus, or a simple pervasive channel based on the second bus, and can quickly switch to another channel when one channel fails.

In addition, especially in a cloud computing bare metal server scenario, the cloud computing provider cannot control the shutdown and restart actions of the user, that is, the cloud computing provider cannot control the state of the specific switching fabric as the first out-of-band management channel, so that the above channel switching greatly improves the reliability of out-of-band management in the bare metal server scenario.

In one example, the out-of-band management transport protocol is a management component transport protocol, MCTP. The first out-of-band management channel is a peripheral component interconnect express (PCIe) -based physical layer channel, and the first out-of-band management channel performs out-of-band management on the target peripheral via the processor control Root Complex (RC). The second out-of-band management channel is a physical layer channel based on a system management bus SMBUS or an integrated circuit bus I2C. The first out-of-band management channel and the second out-of-band management channel belong to different physical layer channels in the same protocol architecture, so that the second out-of-band management channel is adopted to realize the compatibility of the second out-of-band management channel and realize the non-perception of a transmission layer during channel switching.

Fig. 3 is a schematic diagram of an out-of-band management method according to another embodiment of the present invention. As shown, the peripheral out-of-band management system is configured in a specific server, and includes a processor 310, a root complex 320, a management controller 330, and a plurality of peripherals 340, and the server may be disposed in a computer room, for example, may be a bare metal server, or may be a physical server or other virtual server. Processor 310 may be a central processor, for example, and may include a PCIe management engine, which may be implemented as a circuit or module. The root complex 320 device connects the processor and memory subsystem to a PCIe switch fabric composed of one or more switch devices. The RC may have a connection topology as shown. The PCIe management engine may communicate with port 4 of the RC. The peripheral device 340 may be any component other than a processor and a memory, and the peripheral device 340 may be mounted in the form of an external board card, or may be mounted in other forms. Each peripheral 340 communicates with a respective RC port, e.g., peripheral 1, peripheral 2, and peripheral 3 communicate with port 1, port 2, and port 3, respectively. Port 4 of the RC may also communicate with the PCIe interface of management controller 330.

In addition, the management controller 330 also includes an I2C (example of a second bus) interface. The I2C interface communicates with peripheral 1, peripheral 2, and peripheral 3, respectively, and a second out-of-band management channel is used to perform out-of-band management for peripheral 340. It should be understood that the I2C interface may be one or more, for example, the I2C interface may be configured separately for each peripheral 340, corresponding to a plurality of second out-of-band management channels, respectively.

Fig. 4 is a schematic diagram of an out-of-band management method according to another embodiment of the present invention. As shown, the processor may run a host operating system. The host operating system may have installed therein a transport layer driver and an application layer. The transport layer driver includes, but is not limited to, a Non-Volatile Memory Express (NVMe) driver.

The management controller may run a management controller operating system. The management controller operating system may be installed with application layer and transport layer management interface drivers. The transport layer Management Interface driver includes, but is not limited to, a non-volatile memory Management Interface (NVMe-MI) driver. NVM Express is an open collection of standards and information to fully demonstrate the advantages of non-volatile memory in all types of computing environments from mobile devices to data centers.

For the first out-of-band management channel, the management controller communicates with root port B of the processor through root port C. The root port D of the peripheral communicates with the root port a of the processor. Inside the processor, communication takes place between root port B and root port a. Therefore, out-of-band management of the management controller to the external device is realized. In particular, the transport layer management interface drives the encapsulation of the transport layer (such as the out-of-band management transport protocol of MCTP) that enables out-of-band management messages, and transport of the physical layer is enabled through root port C.

For the second out-of-band management channel, the management controller communicates with port F of the peripheral through port E. In particular, the transport layer management interface drives the encapsulation of the transport layer (such as the out-of-band management transport protocol of MCTP) that enables out-of-band management messages, and transport of the physical layer is enabled through root port E.

In addition, the management controller may switch between the port E and the root port C, for example, the management controller includes a physical layer management interface driver, the physical layer management interface driver receives a transport layer encapsulation (e.g., a data packet) from the transport layer management interface driver, and encapsulates the transport layer encapsulation correspondingly according to the current operating state of the processor, so as to obtain a physical layer encapsulation message.

In addition, the management controller may receive control messages from the processor indicating the current operating state of the processor. The management controller may also receive control messages from the power management system indicating the current operating state of the processor.

In addition, if the processor is currently in a normal operation state (e.g., S0 mode of X86 architecture), the first bus corresponding to the root port C is used for encapsulation, resulting in a first physical layer encapsulation message. If the processor is currently in an abnormal operation state (for example, a non-S0 mode of the X86 architecture, that is, any one of S1-S5 modes), the second bus corresponding to the root port C is adopted for encapsulation, and a second physical layer encapsulation message is obtained.

Further, for out-of-band management with the first out-of-band management channel, the processor includes a data information channel and a control information channel. Root port a may be used to transmit control information as well as data information. If root port a is used to transmit data information, root port B may be used to monitor the data transmission of root port a to obtain control information. Therefore, the control information and the data information are separated by using the root port B and the root port A.

In another implementation of the invention, the method further comprises: and if the current channel state of the first out-of-band management channel indicates that the first out-of-band channel is currently effective, switching to the first out-of-band management channel, and performing out-of-band management on the target peripheral.

Because the first out-of-band management channel is used for performing out-of-band management on the target peripheral equipment through the processor, when the current channel state of the first out-of-band management channel indicates that the first out-of-band channel is currently effective, the first out-of-band management channel is switched to, and more reliable out-of-band management can be performed on the target peripheral equipment.

In other words, the Management Controller (MC) and the target peripheral (Managed Device, MD) support the channel based on the first bus and the channel based on the second bus at the same time in the protocol layer of the out-of-band Management transport protocol, and the Management Controller may select to use one channel to issue the out-of-band Management transport protocol message to the target peripheral.

In the system design, the management controller and the target peripheral simultaneously support a first bus hardware interface and a second bus hardware interface, the management control is used as a bus manager of two buses with an out-of-band management transmission protocol, and channel switching is realized through a switching module. The management engine forwards a first out-of-band management message of the management controller to a target peripheral device hanging down from a particular switch fabric as a proxy for an out-of-band management transport protocol.

In another implementation of the present invention, determining a current channel state of a first out-of-band management channel of an out-of-band management transport protocol includes: a current channel state of a first out-of-band management channel of an out-of-band management transport protocol is determined by monitoring a current power management state of a processor.

Because the current power management state of the processor can reflect the current channel state of the first out-of-band management channel, the current channel state of the first out-of-band management channel can be accurately determined while the processor is subjected to power management.

Specifically, the current Power management state may be collected through an Interface such as an Advanced Configuration and Power Interface (ACPI). The ACPI specification defines that an ACPI-compliant computer system may have the following seven states.

In another implementation of the present invention, determining a current channel state of a first out-of-band management channel of an out-of-band management transport protocol includes: and if the current power management state indicates that the processor is in an abnormal operation state, determining the current channel state of a first out-of-band management channel of the out-of-band management transmission protocol as the current failure of the first out-of-band management channel.

When the current power management state indicates that the processor is in an abnormal operation state, the first out-of-band management channel which is subjected to out-of-band management by the processor is unavailable or has poor availability, so that the current failure of the first out-of-band management channel is accurately judged.

Specifically, taking ACPI as an example, in the case of the X86 architecture, the normal operating state includes, but is not limited to, G0 (S0): normal operating state of the computer-both the operating system and the application program are running. CPU(s) executes instructions. In this state (i.e., without entering the G1 sleep mode), the CPU and hard disk, DVD drive, etc. devices may enter and come back from a low power state over and over again, referred to as C0-Cn and D0-D3. For example, for a laptop computer, all currently unused devices are typically turned off when running on a battery; some desktop computers also operate accordingly to reduce noise.

The abnormal operation state includes, but is not limited to, G1 sleep, and can be further divided into four states from S1 to S4. The system wakes up from the states to the G0 with the shortest time required for operation (wake-up waiting time) S1, shorter S2 and S3 and longer S4.

In another implementation manner of the present invention, switching to a first out-of-band management channel to perform out-of-band management on a target peripheral includes: switching to a first out-of-band management channel based on a first bus; the first out-of-band management command is sent to the processor over the first bus such that the processor forwards the first out-of-band management command to the target peripheral over the first bus.

Since the first bus is used for sending the first out-of-band management command to the processor, and the processor forwards the first out-of-band management command to the target peripheral device through the first bus, efficient data transmission is achieved through the first bus.

In another implementation of the invention, switching to a first out-of-band management channel based on a first bus comprises: switching to a first out-of-band management channel based on the first bus based on a mapping relationship between the target peripheral and the first out-of-band management channel, wherein the method further comprises: and if the mapping relation between the target peripheral and the second out-of-band management channel does not exist, establishing the mapping relation between the target peripheral and the second out-of-band management channel based on the mapping relation between the target peripheral and the first out-of-band management channel.

Because the mapping relation between the target peripheral and the second out-of-band management channel is established based on the mapping relation between the target peripheral and the first out-of-band management channel, the unified management of two mapping relations corresponding to the two out-of-band management channels is realized, the switching efficiency between the two out-of-band management channels is improved, and the out-of-band management efficiency is further improved.

In another implementation manner of the present invention, switching to a second out-of-band management channel of an out-of-band management transport protocol to directly perform out-of-band management on a target peripheral device includes: switching to a second out-of-band management channel based on a second bus of the out-of-band management transport protocol; and sending a second out-of-band management command to the target peripheral through a second bus.

And the channel is switched to a second out-of-band management channel based on a second bus of the out-of-band management transmission protocol, so that the rapid switching of the physical layer channel under the out-of-band management transmission protocol is realized. In other words, seamless switching of channels is realized, and good backward compatibility can be performed even with the existing configuration.

In another implementation of the present invention, switching to a second out-of-band management channel of an out-of-band management transport protocol includes: and judging the current channel state of a second out-of-band management channel of the out-of-band management transmission protocol, and switching to the second out-of-band management channel of the out-of-band management transmission protocol if the current channel state of the second out-of-band management channel indicates that the second out-of-band management channel is currently effective.

The current channel state of the second out-of-band management channel can reflect whether the second out-of-band management channel fails currently, so that the second out-of-band management channel is switched to the second out-of-band management channel of the out-of-band management transmission protocol by judging the current channel state of the second out-of-band management channel, and reliable switching operation is realized.

In another implementation of the invention, the method further comprises: and if the current channel state of the second out-of-band management channel indicates that the second out-of-band management channel is currently invalid, restarting is performed until the current channel state of the second out-of-band management channel indicates that the second out-of-band management channel is currently valid.

The current channel state of the second out-of-band management channel can reflect whether the second out-of-band management channel is invalid currently, so that when the second out-of-band management channel is valid currently, the second out-of-band management channel is switched to the second out-of-band management channel of the out-of-band management transmission protocol, and reliable out-of-band management of the target peripheral equipment is realized.

In another implementation of the invention, the method further comprises: and if the current channel state of the second out-of-band management channel indicates that the second out-of-band management channel is invalid currently, reporting a channel fault instruction.

Under the condition that the first out-of-band management channel fails, the current failure of the second out-of-band management channel can accurately reflect the fault of the reporting channel, so that the reporting channel fault instruction is favorable for eliminating the channel fault.

In another implementation of the present invention, determining a current channel status of a second outband management channel of an outband management transport protocol includes: and judging the current channel state of the second out-of-band management channel based on the mapping relation between the target peripheral and the second out-of-band management channel of the out-of-band management transmission protocol.

Since the mapping relationship between the target peripheral and the second out-of-band management channel of the out-of-band management transport protocol is important out-of-band management information, the current channel state of the second out-of-band management channel is judged based on the mapping relationship between the target peripheral and the second out-of-band management channel of the out-of-band management transport protocol, and influence factors of out-of-band management except the current channel state of the second out-of-band management channel can be effectively eliminated.

In another implementation of the invention, the method further comprises: and if the mapping relation between the target peripheral and the second out-of-band management channel does not exist, establishing the mapping relation between the target peripheral and the second out-of-band management channel based on the mapping relation between the target peripheral and the first out-of-band management channel.

Based on the mapping relationship between the target peripheral and the first out-of-band management channel, the mapping relationship between the target peripheral and the second out-of-band management channel can be accurately and reliably established, and the management of the out-of-band management channel is facilitated, so that the switching operation such as the out-of-band management channel is performed.

In another implementation of the invention, the method further comprises: and if the mapping relation between the target peripheral and the first out-of-band management channel does not exist, directly creating the mapping relation between the target peripheral and the first out-of-band management channel and the mapping relation between the target peripheral and the second out-of-band management channel.

The method includes the steps that the mapping relation between the target peripheral and the first out-of-band management channel and the mapping relation between the target peripheral and the second out-of-band management channel are directly created, out-of-band management can be conducted through the second out-of-band management channel based on the mapping relation between the target peripheral and the second out-of-band management channel, when the first out-of-band management channel is switched to the first out-of-band management channel, the mapping relation between the target peripheral and the first out-of-band management channel does not need to be created, out-of-band management can be conducted through the first out-of-band management channel directly based on the mapping relation, and the management efficiency of the out-of-band management channel is improved.

Fig. 5A is a schematic flow chart of an out-of-band management method according to another embodiment of the present invention. In this example, the first bus may be a PCIe bus. The second bus may be an SMBUS bus or an I2C bus. It should be understood that the various steps in this example are merely exemplary, and in other examples, some steps may be added, some steps may be reduced, or some steps may be replaced.

In step 511, the current channel state of the first out-of-band management channel is queried and step 512 is entered.

In step 512, determine if the current lane status of the first out-of-band management lane indicates that the lane is available? If not, proceed to step 515; if so, proceed to step 513.

In step 513, a correspondence table between the first mapping relationship and the second mapping relationship is queried, and the process proceeds to step 514.

In step 514, a first out-of-band management command is sent over the first bus.

In step 515, the channel status of the second out-of-band management channel is queried and step 516 is entered.

In step 516, determine if the current channel status of the second out-of-band management channel indicates that the channel is available? If yes, go to step 517; if not, proceed to step 518.

In step 517, a second out-of-band management command is transmitted over the second bus.

In step 518, a channel failure is reported. For example, if the second out-of-band management channel fails, the management controller C reports an error to the system management application, e.g., to a monitoring server of the data center.

Fig. 5B is a schematic flow chart of an out-of-band management method according to another embodiment of the present invention. In this example, the first bus may be a PCIe bus. The second bus may be an SMBUS bus or an I2C bus. It should be understood that the various steps in this example are merely exemplary, and in other examples, some steps may be added, some steps may be reduced, or some steps may be replaced.

In step 521, the baseband management controller is started, and the process proceeds to step 522.

In step 522, determine if the processor is in a normal operating state? If yes, go to step 523; if not, proceed to step 525.

Specifically, the management controller firstly queries the ACPI power state of the processor, and if the ACPI power state is SO, the ACPI power state is in a normal operation state; otherwise, the operation is in an abnormal operation state.

Specifically, if the processor is already in the S0 state, the state of the first out-of-band management channel of each peripheral is queried, and the first out-of-band management message is sent directly if the channel is normal.

In step 523, the current channel state of the first out-of-band management channel is queried and step 524 is entered.

In step 524, determine if the current lane status of the first out-of-band management lane indicates that the lane is available? If so, go to step 526; if not, proceed to step 525.

Specifically, if the processor is not in the S0 state, device discovery and MCTP messaging is performed directly over the second bus.

In step 525, the current channel state of the second out-of-band management channel is queried and step 528 is entered.

In step 526, a second mapping relationship is created based on the first mapping relationship.

In step 527, a first out-of-band management command is sent over the first bus.

In step 528, address assignment is performed based on device discovery of the peripheral of the second out-of-band management channel and a second mapping relationship is created and the process proceeds to step 529. It should be understood that the first mapping relationship may be further created by a second mapping relationship.

In step 529, it is determined whether the current channel status of the second out-of-band management channel indicates that the channel is available? If yes, go to step 530; if not, proceed to step 531.

In step 530, a second out-of-band management command is sent over the second bus. For example, if the channel is not normal, the second out-of-band management message is issued according to the corresponding relationship between the first mapping relationship and the second mapping relationship.

In step 531, a channel failure is reported. For example, if the second out-of-band management channel fails, the management controller C reports an error to the system management application, e.g., to a monitoring server of the data center.

Fig. 6 is a schematic block diagram of an out-of-band management apparatus according to another embodiment of the present invention. The out-of-band management apparatus of fig. 6 includes:

a determining module 610, configured to determine a current channel state of a first out-of-band management channel of an out-of-band management transport protocol, where the first out-of-band management channel is used for performing out-of-band management on a target peripheral device via a processor;

the management module 620, if the current channel status of the first out-of-band management channel indicates that the first out-of-band channel is currently disabled, switches to a second out-of-band management channel of the out-of-band management transmission protocol, and directly performs out-of-band management on the target peripheral.

In another implementation of the present invention, the management module is further configured to: and if the current channel state of the first out-of-band management channel indicates that the first out-of-band channel is currently effective, switching to the first out-of-band management channel, and performing out-of-band management on the target peripheral.

In another implementation manner of the present invention, the determining module is specifically configured to: a current channel state of a first out-of-band management channel of an out-of-band management transport protocol is determined by monitoring a current power management state of a processor.

In another implementation manner of the present invention, the determining module is specifically configured to: and if the current power management state indicates that the processor is in an abnormal operation state, determining the current channel state of a first out-of-band management channel of the out-of-band management transmission protocol as the current failure of the first out-of-band management channel.

In another implementation manner of the present invention, the management module is specifically configured to: switching to a first out-of-band management channel based on a first bus; the first out-of-band management command is sent to the processor over the first bus such that the processor forwards the first out-of-band management command to the target peripheral over the first bus.

In another implementation manner of the present invention, the management module is specifically configured to: based on the mapping relationship between the target peripheral and the first out-of-band management channel, switching to the first out-of-band management channel based on the first bus, the management module further configured to: and if the mapping relation between the target peripheral and the second out-of-band management channel does not exist, establishing the mapping relation between the target peripheral and the second out-of-band management channel based on the mapping relation between the target peripheral and the first out-of-band management channel.

In another implementation manner of the present invention, the management module is specifically configured to: switching to a second out-of-band management channel based on a second bus of the out-of-band management transport protocol; and sending a second out-of-band management command to the target peripheral through a second bus.

In another implementation manner of the present invention, the management module is specifically configured to: and judging the current channel state of a second out-of-band management channel of the out-of-band management transmission protocol, and switching to the second out-of-band management channel of the out-of-band management transmission protocol if the current channel state of the second out-of-band management channel indicates that the second out-of-band management channel is currently effective.

In another implementation of the present invention, the management module is further configured to: and if the current channel state of the second out-of-band management channel indicates that the second out-of-band management channel is currently invalid, restarting is performed until the current channel state of the second out-of-band management channel indicates that the second out-of-band management channel is currently valid.

In another implementation of the present invention, the management module is further configured to: and if the current channel state of the second out-of-band management channel indicates that the second out-of-band management channel is invalid currently, reporting a channel fault instruction.

In another implementation manner of the present invention, the management module is specifically configured to: and judging the current channel state of the second out-of-band management channel based on the mapping relation between the target peripheral and the second out-of-band management channel of the out-of-band management transmission protocol.

In another implementation of the present invention, the management module is further configured to: and if the mapping relation between the target peripheral and the second out-of-band management channel does not exist, establishing the mapping relation between the target peripheral and the second out-of-band management channel based on the mapping relation between the target peripheral and the first out-of-band management channel.

In another implementation of the present invention, the management module is further configured to: and if the mapping relation between the target peripheral and the first out-of-band management channel does not exist, directly creating the mapping relation between the target peripheral and the first out-of-band management channel and the mapping relation between the target peripheral and the second out-of-band management channel.

The apparatus of this embodiment is used to implement the corresponding method in the foregoing method embodiments, and has the beneficial effects of the corresponding method embodiments, which are not described herein again. In addition, the functional implementation of each module in the apparatus of this embodiment can refer to the description of the corresponding part in the foregoing method embodiment, and is not described herein again.

Fig. 7 is a schematic configuration diagram of a management controller for out-of-band management according to another embodiment of the present invention. The management controller includes a bus interface 710, a communication interface 720, and a switching circuit 730. The communication interface 720 is configured to determine a current channel status of a first out-of-band management channel of an out-of-band management transport protocol, wherein the first out-of-band management channel is configured to manage a target peripheral out-of-band via a processor. If the current channel status of the first out-of-band management channel indicates that the first out-of-band channel is currently disabled, the switching circuit 730 is configured to switch to a second out-of-band management channel of the out-of-band management transport protocol, and the bus interface 710 is configured to directly perform out-of-band management on the target peripheral.

In another implementation of the present invention, the management controller further comprises: and the encapsulating circuit is used for encapsulating the out-of-band management transmission layer message by adopting a physical layer protocol of the second out-of-band management channel and sending the encapsulated message to the bus interface.

In another implementation of the invention, the encapsulation circuit encapsulates the out-of-band management transport layer message using a physical layer protocol of the first out-of-band management channel and sends the encapsulated message to the processor for out-of-band management of the target peripheral device via the processor if the current channel state of the first out-of-band management channel indicates that the first out-of-band channel is currently active. Therefore, the second out-of-band management channel is adopted to realize the non-perception of the transmission layer during channel switching.

Fig. 8 is a schematic configuration diagram of a management system for out-of-band management according to another embodiment of the present invention. The management system includes a management controller 810 and a processor 820. The management system may also include one or more peripherals.

Management controller 810 includes a first bus interface 813, a second bus interface 812, a communication interface 811, and a switching circuit 814. The communication interface 811 is configured to determine a current channel state of a first out-of-band management channel of an out-of-band management transport protocol, where the first out-of-band management channel is configured to perform out-of-band management of a target peripheral via a processor. If the current channel status of the first out-of-band management channel indicates that the first out-of-band channel is currently disabled, the switching circuit 814 is configured to switch to a second out-of-band management channel of the out-of-band management transport protocol, and the second bus interface 812 is configured to directly perform out-of-band management on the target peripheral.

Processor 820 includes a first bus interface 821. First bus interface 821 may communicate with a first bus interface 813.

One or more of the peripherals may be configured with a first bus management interface and a second bus management interface, respectively, which may be in communication with first bus interface 821 and first bus interface 813, respectively, for enabling data information transfer and control information transfer, respectively. The second bus management interface may communicate control information with the second bus interface 812 to enable out-of-band management.

The Processor described herein may be a general-purpose Processor, and includes a Central Processing Unit (CPU), a Network Processor (NP), and the like; but may also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an off-the-shelf programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic, discrete hardware components. The various methods, steps and logic blocks disclosed in the embodiments of the present invention may be implemented or performed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.

The storage medium may be, but is not limited to, a Random Access Memory (RAM), a Read Only Memory (ROM), a Programmable Read Only Memory (PROM), an Erasable Read Only Memory (EPROM), an electrically Erasable Read Only Memory (EEPROM), and the like.

In particular, according to an embodiment of the present disclosure, the processes described above with reference to the flowcharts may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program embodied on a storage medium, the computer program comprising program code configured to perform the method illustrated by the flow chart. In such an embodiment, the computer program may be downloaded and installed from a network via the communication section, and/or installed from a removable medium. The computer program performs the above-described functions defined in the method of the present invention when executed by a Central Processing Unit (CPU). It should be noted that the storage medium of the present invention can be a computer-readable signal medium or a computer-readable storage medium or any combination of the two. The storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a random access storage media (RAM), a read-only storage media (ROM), an erasable programmable read-only storage media (EPROM or flash memory), an optical fiber, a portable compact disc read-only storage media (CD-ROM), an optical storage media piece, a magnetic storage media piece, or any suitable combination of the foregoing. In the present invention, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In the present invention, however, a computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any storage medium that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a storage medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, fiber optic cable, RF, etc., or any suitable combination of the foregoing.

Computer program code configured to carry out operations for aspects of the present invention may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may operate over any of a variety of networks: including a Local Area Network (LAN) or a Wide Area Network (WAN) -to the user's computer, or alternatively, to an external computer (e.g., through the internet using an internet service provider).

The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions configured to implement the specified logical function(s). In the above embodiments, specific precedence relationships are provided, but these precedence relationships are only exemplary, and in particular implementations, the steps may be fewer, more, or the execution order may be modified. That is, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

The modules described in the embodiments of the present invention may be implemented by software or hardware. The names of these modules do not in some cases constitute a limitation of the module itself.

As another aspect, the present invention also provides a storage medium having stored thereon a computer program which, when executed by a processor, implements the method as described in the above embodiments.

As another aspect, the present invention also provides a storage medium, which may be contained in the apparatus described in the above embodiments; or may be present separately and not assembled into the device. The storage medium carries one or more programs that, when executed by the apparatus, cause the apparatus to: determining a current channel state of a first out-of-band management channel of an out-of-band management transport protocol, wherein the first out-of-band management channel is used for out-of-band management of a target peripheral via a processor; and if the current channel state of the first out-of-band management channel indicates that the first out-of-band channel is failed currently, switching to a second out-of-band management channel of the out-of-band management transmission protocol, and directly performing out-of-band management on the target peripheral.

The expressions "first", "second", "said first" or "said second" used in various embodiments of the present disclosure may modify various components regardless of order and/or importance, but these expressions do not limit the respective components. The above description is only configured for the purpose of distinguishing elements from other elements. For example, the first user equipment and the second user equipment represent different user equipment, although both are user equipment. For example, a first element could be termed a second element, and, similarly, a second element could be termed a first element, without departing from the scope of the present disclosure.

When an element (e.g., a first element) is referred to as being "operably or communicatively coupled" or "connected" (operably or communicatively) to "another element (e.g., a second element) or" connected "to another element (e.g., a second element), it is understood that the element is directly connected to the other element or the element is indirectly connected to the other element via yet another element (e.g., a third element). In contrast, it is understood that when an element (e.g., a first element) is referred to as being "directly connected" or "directly coupled" to another element (a second element), no element (e.g., a third element) is interposed therebetween.

The foregoing description is only exemplary of the preferred embodiments of the invention and is illustrative of the principles of the technology employed. It will be appreciated by those skilled in the art that the scope of the invention according to the present invention is not limited to the specific combination of the above-mentioned features, but also encompasses other embodiments in which any combination of the above-mentioned features or their equivalents is possible without departing from the scope of the invention as defined by the appended claims. For example, the above features and (but not limited to) features having similar functions disclosed in the present invention are mutually replaced to form the technical solution.

Claims

1. An out-of-band management method, comprising:

determining a current channel state of a first out-of-band management channel of an out-of-band management transport protocol, wherein the first out-of-band management channel is used for out-of-band management of a target peripheral via a processor;

and if the current channel state of the first out-of-band management channel indicates that the first out-of-band channel is failed currently, switching to a second out-of-band management channel of the out-of-band management transmission protocol, and directly performing out-of-band management on the target peripheral.

2. The method of claim 1, wherein the method further comprises:

and if the current channel state of the first out-of-band management channel indicates that the first out-of-band channel is currently effective, switching to the first out-of-band management channel, and performing out-of-band management on the target peripheral.

3. The method of claim 1, wherein the determining a current channel state of a first out-of-band management channel of an out-of-band management transport protocol comprises:

determining a current channel state of a first out-of-band management channel of an out-of-band management transport protocol by monitoring a current power management state of the processor.

4. The method of claim 3, wherein the determining a current channel state of a first out-of-band management channel of an out-of-band management transport protocol comprises:

and if the current power management state indicates that the processor is in an abnormal operation state, determining the current channel state of a first out-of-band management channel of the out-of-band management transmission protocol as the current failure of the first out-of-band management channel.

5. The method of claim 2, wherein the switching to the first out-of-band management channel for out-of-band management of a target peripheral comprises:

switching to a first out-of-band management channel based on a first bus;

sending a first out-of-band management command to the processor over the first bus, such that the processor forwards the first out-of-band management command to the target peripheral over the first bus.

6. The method of claim 5, wherein the switching to the first out-of-band management channel based on the first bus comprises:

switching to a first out-of-band management channel based on a first bus based on a mapping relationship between the target peripheral and the first out-of-band management channel, wherein the method further comprises:

and if the mapping relation between the target peripheral and the second out-of-band management channel does not exist, establishing the mapping relation between the target peripheral and the second out-of-band management channel based on the mapping relation between the target peripheral and the first out-of-band management channel.

7. The method of claim 1, wherein said switching to a second out-of-band management channel of the out-of-band management transport protocol for direct out-of-band management of the target peripheral device comprises:

switching to a second out-of-band management channel based on a second bus of the out-of-band management transport protocol;

and sending a second out-of-band management command to the target peripheral through the second bus.

8. The method of claim 1, wherein the switching to the second out-of-band management channel of the out-of-band management transport protocol comprises:

and judging the current channel state of a second out-of-band management channel of the out-of-band management transmission protocol, and if the current channel state of the second out-of-band management channel indicates that the second out-of-band management channel is currently effective, switching to the second out-of-band management channel of the out-of-band management transmission protocol.

9. The method of claim 8, wherein the method further comprises:

and if the current channel state of the second out-of-band management channel indicates that the second out-of-band management channel is currently invalid, executing restart until the current channel state of the second out-of-band management channel indicates that the second out-of-band management channel is currently valid.

10. The method of claim 9, wherein the method further comprises:

and reporting a channel fault instruction if the current channel state of the second out-of-band management channel indicates that the second out-of-band management channel is currently invalid.

11. The method of claim 8, wherein the determining a current channel state of a second out-of-band management channel of the out-of-band management transport protocol comprises:

and judging the current channel state of a second out-of-band management channel based on the mapping relation between the target peripheral and the second out-of-band management channel of the out-of-band management transmission protocol.

12. The method of claim 11, wherein the method further comprises:

13. The method of claim 12, wherein the method further comprises:

and if the mapping relation between the target peripheral and the first out-of-band management channel does not exist, directly creating the mapping relation between the target peripheral and the first out-of-band management channel and the mapping relation between the target peripheral and the second out-of-band management channel.

14. The method of claim 1, wherein the out-of-band management transport protocol is a Management Component Transport Protocol (MCTP),

wherein the first out-of-band management channel is a peripheral component interconnect express (PCIe) -based physical layer channel that manages the target peripheral out-of-band via the processor control Root Complex (RC),

the second out-of-band management channel is a physical layer channel based on a system management bus SMBUS or an integrated circuit bus I2C.

15. An out-of-band management device comprising:

the device comprises a determining module, a judging module and a judging module, wherein the determining module is used for determining the current channel state of a first out-of-band management channel of an out-of-band management transmission protocol, and the first out-of-band management channel is used for carrying out-of-band management on a target peripheral through a processor;

and the management module is used for switching to a second out-of-band management channel of the out-of-band management transmission protocol to directly perform out-of-band management on the target peripheral equipment if the current channel state of the first out-of-band management channel indicates that the first out-of-band channel is failed currently.

16. A management controller, comprising:

a bus interface, a communication interface and a switching circuit,

wherein the communication interface is to determine a current channel state of a first out-of-band management channel of an out-of-band management transport protocol, wherein the first out-of-band management channel is to perform out-of-band management of a target peripheral via a processor,

wherein, if the current channel status of the first out-of-band management channel indicates that the first out-of-band channel is currently disabled, the switching circuit is configured to switch to a second out-of-band management channel of the out-of-band management transport protocol, and the bus interface is configured to directly perform out-of-band management on the target peripheral.

17. The management controller of claim 16, further comprising: and the encapsulating circuit is used for encapsulating the out-of-band management transmission layer message by adopting the physical layer protocol of the second out-of-band management channel and sending the encapsulated message to the bus interface.

18. The management controller of claim 17, wherein the encapsulation circuit encapsulates an out-of-band management transport layer message in a physical layer protocol of the first out-of-band management channel and sends the encapsulated message to the processor for out-of-band management of a target peripheral via the processor if the current channel state of the first out-of-band management channel indicates that the first out-of-band channel is currently active.

19. A management system, comprising: the management controller and processor of any of claims 16-18.

20. A storage medium having stored thereon a computer program which, when executed by control circuitry, implements the method of any one of claims 1 to 14.