CN112256603B

CN112256603B - Server and expansion equipment based on OCP

Info

Publication number: CN112256603B
Application number: CN202011184943.6A
Authority: CN
Inventors: 张世强
Original assignee: Inspur Electronic Information Industry Co Ltd
Current assignee: Inspur Electronic Information Industry Co Ltd
Priority date: 2020-10-29
Filing date: 2020-10-29
Publication date: 2023-02-28
Anticipated expiration: 2040-10-29
Also published as: CN112256603A

Abstract

The application discloses expansion equipment based on OCP includes: the OCP connector golden finger is connected with the OCP slot of the server; the first controller is connected with the OCP connector golden finger and used for converting the PCIE signal into an IDE signal so that the server stores data by utilizing the N CF cards; n CF card connectors connected with the first controller; n CF cards connected with the N CF card connectors respectively; wherein N is a positive integer. By the scheme, the vacancy condition of the OCP slot position is avoided, the storage performance of the server is improved, the CF card supports plug-and-play, the use is also very convenient, and the server has the corresponding technical effect.

Description

Server and expansion equipment based on OCP

Technical Field

The invention relates to the technical field of computers, in particular to a server and expansion equipment based on an OCP (optical communications protocol).

Background

An OCP (OPEN computer Project) network card is used as a sandwich card, which is a supplement to the original network card of the server, and is widely used in the server. The network communication of single host or multi host can be generally carried out through an OCP network card, and in addition, a server storage interface is generally designed in a server mainboard and used for data storage or system startup through a memory card.

In some situations, the service of the client does not need an additional network card function of the OCP network card, and the OCP network card will leave a vacant position, which will cause a waste. With the comprehensive and wide application of the server, the requirement on the performance of the server is higher and higher, the server mainboard resources are more and more, the wiring challenge is larger and larger, the solution of the waste condition is favorable for setting devices and wiring in the server, and the performance of the server is improved.

In summary, how to effectively avoid the position vacancy caused by not needing the OCP network card is a technical problem that needs to be solved urgently by those skilled in the art.

Disclosure of Invention

The invention aims to provide a server and an OCP-based expansion device, so as to effectively avoid position vacancy caused by the fact that an OCP network card is not needed.

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

an OCP-based expansion device, comprising:

the OCP connector golden finger is connected with the OCP slot of the server;

the first controller is connected with the OCP connector golden finger and used for converting the PCIE signal into an IDE signal so that the server stores data by utilizing N CF cards;

n CF card connectors connected with the first controller;

n CF cards connected with the N CF card connectors respectively; wherein N is a positive integer.

Preferably, N =2.

Preferably, the method further comprises the following steps:

the second controller is respectively connected with the OCP connector golden finger, the first CF card connector and the second CF card connector and is used for:

determining the in-place state information of a first CF card through the first CF card connector and sending the in-place state information to a central processing unit, and determining the in-place state information of a second CF card through the second CF card connector and sending the in-place state information to the central processing unit; controlling the master-slave relationship between the first CF card and the second CF card according to the received master-slave control instruction;

the master-slave control instruction is issued by the central processing unit based on the in-place state information of the first CF card and the in-place state information of the second CF card.

Preferably, the method further comprises the following steps:

the jumper device is connected with the second controller and is used for sending an electric signal to the second controller;

the second controller is further configured to: when the received master-slave control instruction is the master-slave control instruction carrying the control content, the master-slave relationship between the first CF card and the second CF card is controlled according to the received master-slave control instruction, and when the received master-slave control instruction is the master-slave control instruction not carrying the control content, the master-slave relationship between the first CF card and the second CF card is controlled according to the electric signal sent by the jumper device.

Preferably, when the in-place state information of the first CF card is that the first CF card is in place and has good contact, and the in-place state information of the second CF card is that the second CF card is in place and has good contact, the master-slave control instruction received by the second controller is a master-slave control instruction not carrying control content;

when the in-place state information of the first CF card is that the first CF card is in place and has good contact, and meanwhile, the in-place state information of the second CF card is that the second CF card is not in place, the master-slave control instruction received by the second controller is a master-slave control instruction carrying control content, so that the second controller controls the first CF card to be master equipment and the second CF card to be slave equipment according to the received master-slave control instruction;

when the in-place state information of the first CF card is specifically that the first CF card is not in place, and meanwhile, the in-place state information of the second CF card is specifically that the second CF card is in place and has good contact, the master-slave control instruction received by the second controller is a master-slave control instruction carrying control content, so that the second controller controls the first CF card to be a slave device according to the received master-slave control instruction and controls the second CF card to be a master device.

Preferably, the method further comprises the following steps: and the display device is used for displaying the in-place state information of the first CF card and the in-place state information of the second CF card.

Preferably, when the in-place state information of the first CF card specifically indicates that the first CF card is not in place, and the in-place state information of the second CF card specifically indicates that the second CF card is not in place, the master-slave control instruction received by the second controller is a master-slave control instruction that does not carry control content;

when the in-place state information of the first CF card is specifically the first CF card is in place and has poor contact, and meanwhile, the in-place state information of the second CF card is specifically the second CF card is not in place, a master-slave control instruction received by the second controller is a master-slave control instruction carrying control content, so that the second controller controls the first CF card to be master equipment and the second CF card to be slave equipment according to the received master-slave control instruction;

when the in-place state information of the first CF card is specifically that the first CF card is not in place, and meanwhile, the in-place state information of the second CF card is specifically that the second CF card is in place and has poor contact, the master-slave control instruction received by the second controller is a master-slave control instruction carrying control content, so that the second controller controls the first CF card to be a slave device according to the received master-slave control instruction and controls the second CF card to be a master device.

Preferably, the second controller is a CPLD controller.

A server, comprising any one of the OCP-based expansion devices described above.

By applying the technical scheme provided by the embodiment of the invention, considering the situation that the position of the OCP network card is vacant, at least 2 CF cards can be usually placed at the position, the CF cards support plug and play, the storage application is very convenient, and meanwhile, the storage requirement of the server is higher and higher, so that N CF cards are arranged in the OCP slot of the server. CF card can not be direct with OCP slot connection, consequently this application has set up the OCP connector golden finger with the OCP slot connection of server to can draw forth the PCIE signal of OCP slot, recycle first controller and OCP connector golden finger and be connected, the IDE signal is supported to the CF card, and first controller converts the PCIE signal into the IDE signal, thereby makes the server can utilize a N CF card to carry out data storage. And the connection with the N CF card connectors is realized through the N CF card connectors connected with the first controller. To sum up, when the scheme of this application does not need the OCP network card in the server, set up N CF, avoided the vacancy condition of this position, and be favorable to improving the storage performance of server to the CF card supports plug-and-play, and it is also very convenient to use.

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 embodiments or the prior art descriptions will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.

FIG. 1 is a schematic structural diagram of an expansion device based on OCP in the present invention;

FIG. 2 is a schematic diagram of a port of a CF card connector according to an embodiment of the present invention;

fig. 3 is a schematic structural diagram of an OCP-based expansion device according to an embodiment of the present invention;

fig. 4 is a schematic structural diagram of a jumper device according to an embodiment of the invention.

Detailed Description

The core of the invention is to provide an OCP-based expansion device, which avoids the vacancy of the position of an OCP slot, is beneficial to improving the storage performance of a server, and the CF card supports plug and play and is very convenient to use.

In order that those skilled in the art will better understand the disclosure, reference will now be made in detail to the embodiments of the disclosure as illustrated in the accompanying drawings. It is to be understood that the described embodiments are merely exemplary of the invention, and not restrictive of the full scope of the invention. All other embodiments, which can be obtained by a person skilled in the art without making any creative effort based on the embodiments in the present invention, belong to the protection scope of the present invention.

Referring to fig. 1, fig. 1 is a schematic structural diagram of an OCP-based expansion device according to the present invention, where the OCP-based expansion device may include:

an OCP connector golden finger 10 connected with an OCP slot of the server;

the first controller 20 is connected with the OCP connector golden finger 10 and used for converting the PCIE signal into an IDE signal so that the server stores data by using the N CF cards;

n CF card connectors connected to the first controller 20;

Specifically, an OCP slot of the server may also be generally referred to as an OCP connector of a server motherboard, the OCP connector gold finger 10 of the present application may be connected to the OCP slot of the server, so as to implement extraction of a PCIE signal and an I2C signal in the OCP slot, and also supply power to related devices of the present invention, and further provide a clock signal, which is generally a 50M clock signal, for example, in the embodiment of fig. 3, the second controller 50 may receive a CLK signal of the OCP connector gold finger 10, and perform data interaction with the connector gold finger 10 through the I2C signal. The OCP connector gold finger 10 may be of a standard design.

Because the CF card supports IDE signals, the first controller 20 is connected to the OCP connector gold finger 10, and the first controller 20 can convert PCIE signals into IDE signals, so that the server can utilize N CF cards to perform data storage, that is, the server motherboard can perform data interaction with corresponding CF cards through the first controller 20 and the CF card connector, so that the CF cards exert a storage effect.

The N CF card connectors are connected to the first controller 20, and each CF card connector is connected to a corresponding CF card, that is, a total of N CF cards may be provided. Each CF card connector generally needs to conform to the standard specification of Compact Flash specification, for example, fig. 2 is a schematic port diagram of a CF card connector in an embodiment, and the corresponding names of the pins 1 to 50 can be referred to in table one.

Table one:

n is a positive integer, but in practical applications, the space of the OCP slot is limited, and the space generally allows 1 to 2 CF cards to be placed, and the storage performance of the server is improved by placing 2 CF cards compared with placing 1 CF card, so in practical applications, N of the present application may be generally set to 2. In the embodiment of fig. 1 and 3 of the present application, N is 2, that is, the present invention includes a first CF card connector 31, a first CF card 41 connected to the first CF card connector 31, a second CF card connector 32, and a second CF card 42 connected to the second CF card connector 32.

In addition, it should be noted that, in the N CF cards, it is necessary to determine one CF card as a master device, and the remaining CF cards as slave devices, and the master device is used to implement the start of each CF card. Of course, when there are only 1 CF card, the CF card as a master does not need to be provided with a slave. For the embodiment of fig. 1, the first controller 20 may be in communication connection with each CF card, and set the master device and each slave device in the N CF cards, that is, perform data transmission through PCIE, so as to implement setting of the master device and the slave device, where a specific setting rule may be set and adjusted according to actual needs. Of course, in some embodiments described later, since the second controller 50 is provided, it is not necessary to perform master-slave setting by using the first controller 20, and it is possible to perform master-slave setting by using the second controller 50, which is more convenient to implement.

In an embodiment of the present invention, referring to fig. 3, the method may further include:

a second controller 50 connected to the OCP connector gold finger 10, the first CF card connector 31 and the second CF card connector 32, respectively, for:

determining the in-place state information of the first CF card 41 through the first CF card connector 31 and sending the information to the central processing unit, and determining the in-place state information of the second CF card 42 through the second CF card connector 32 and sending the information to the central processing unit; controlling the master-slave relationship between the first CF card 41 and the second CF card 42 according to the received master-slave control instruction;

the master-slave control instruction is issued by the cpu based on the in-place status information of the first CF card 41 and the in-place status information of the second CF card 42.

In this embodiment, the second controller 50 may determine the in-place status information of the first CF card 41 and send the in-place status information to the central processing unit, and may determine the in-place status information of the second CF card 42 and send the in-place status information to the central processing unit, so as to control the master-slave relationship between the first CF card 41 and the second CF card 42 according to the received master-slave control instruction, where the master-slave control instruction is based on the in-place status information of the first CF card 41 and the in-place status information of the second CF card 42, so that the scheme of the present application can better meet the current issue condition of the in-place status of the first CF card 41 and the second CF card 42 when controlling the master-slave relationship between the first CF card 41 and the second CF card 42.

Further, in an embodiment of the present invention, the method may further include:

a jumper 60 connected to the second controller 50 for transmitting an electrical signal to the second controller 50;

the second controller 50 is also configured to: when the received master-slave control instruction is a master-slave control instruction carrying control content, the master-slave relationship between the first CF card 41 and the second CF card 42 is controlled according to the received master-slave control instruction, and when the received master-slave control instruction is a master-slave control instruction not carrying control content, the master-slave relationship between the first CF card 41 and the second CF card 42 is controlled according to an electric signal sent by the jumper device 60.

In the foregoing embodiment, the master-slave relationship between the first CF card 41 and the second CF card 42 may be controlled by a master-slave control instruction issued by the central controller, and in this embodiment, the master-slave relationship between the first CF card 41 and the second CF card 42 may also be triggered mechanically, that is, a worker may manually select the master-slave relationship between the first CF card 41 and the second CF card 42 through the jumper 60.

It should be noted that in this embodiment, only when the received master-slave control instruction is a master-slave control instruction that does not carry control content, the second controller 50 controls the master-slave relationship between the first CF card 41 and the second CF card 42 according to the electrical signal sent by the jumper 60, that is, the priority of the master-slave control instruction is higher, so as to avoid the problem caused by manual setting in some occasions.

The specific circuit structure of the jumper 60 can be set and adjusted according to actual needs, as long as the purpose of this embodiment can be achieved, that is, the second controller 50 can control the master-slave relationship between the first CF card 41 and the second CF card 42 according to the electrical signal sent by the jumper 60. For example, fig. 4 is a schematic structural diagram of the jumper device 60 according to an embodiment, the level state of the pin D0 can be changed by setting on and off between the

pins

1 and 2 of the CN2, and the level state of the pin D1 can be changed by setting on and off between the

pins

3 and 4 of the CN 2. The level state of pin D0 and the level state of pin D1 are the content of the electrical signal transmitted by the jumper in this embodiment.

The central processing unit issues a master-slave control instruction based on the in-place status information of the first CF card 41 and the in-place status information of the second CF card 42, and the second controller 50 controls the master-slave relationship between the first CF card 41 and the second CF card 42 according to the received master-slave control instruction, where a specific rule may be set according to actual needs, but it can be understood that usually, a CF card with good contact should be set in place and used as a master device.

For example, in an embodiment of the present invention, when the in-place status information of the first CF card 41 is that the first CF card 41 is in place and in good contact, and meanwhile, the in-place status information of the second CF card 42 is that the second CF card 42 is in place and in good contact, the master/slave control instruction received by the second controller 50 is a master/slave control instruction that does not carry control content;

when the in-place state information of the first CF card 41 is that the first CF card 41 is in place and makes good contact, and the in-place state information of the second CF card 42 is that the second CF card 42 is not in place, the master-slave control instruction received by the second controller 50 is a master-slave control instruction carrying control content, so that the second controller 50 controls the first CF card 41 as a master device and the second CF card 42 as a slave device according to the received master-slave control instruction;

when the in-place status information of the first CF card 41 is that the first CF card 41 is not in place, and the in-place status information of the second CF card 42 is that the second CF card 42 is in place and has good contact, the master-slave control instruction received by the second controller 50 is a master-slave control instruction carrying control content, so that the second controller 50 controls the first CF card 41 as a slave device and the second CF card 42 as a master device according to the received master-slave control instruction.

For easy understanding, reference may be made to table two, which shows specific situations where the in-place status information of the first CF card 41 and the second CF card 42 may occur in a specific case.

A second table:

CF card bit status information	D7	D6	D5	D4
					(1) The double cards are in place and have good contact	0	0	1	1
(2) Both cards are in place and only the first CF card 41 makes good contact	1	0	1	1
					(3) Both cards are in place and only the second CF card 42 makes good contact	0	1	1	1
(4) The double cards are in place and the contact of the double cards is poor	1	1	1	1
					(5) Only the first CF card 41 is in place and the first CF card 41 has a bad contact	0	1	0	1
(6) Only the first CF card 41 is in place and the first CF card 41 is in good contact	0	0	0	1
					(7) Only the second CF card 42 is in place and the second CF card 42 has a bad contact	1	0	1	0
(8) Only the second CF card 42 is in place and the second CF card 42 makes good contact	0	0	1	0
					(9) Neither card is in place	0	0	0	0

D4 to D7 are specifically the 4 th to 7 th bit values of the target register in the second controller 50. And D4=1, indicating that the first CF card 41 is in place, D4=0, indicating that the first CF card 41 is not in place. D5=1 indicating that the second CF card 42 is in place, and D5=0 indicating that the second CF card 42 is not in place. D6=1, indicating that the first CF card 41 is abnormal, specifically, that the first CF card 41 is in poor contact, i.e., not inserted. D6=0, which indicates that the first CF card 41 is normal, specifically, D6=0 when the first CF card 41 is in good contact or the first CF card 41 is not inserted. D7=1, indicating that the second CF card 42 is abnormal, specifically, that the second CF card 42 is in poor contact, i.e., not plugged. D7=0, indicating that the second CF card 42 is normal, specifically, when the second CF card 42 is in good contact, or when the second CF card 42 is not inserted, D7= 0.

The in-place status information of the first CF card 41 may be generally determined based on the CD1 and CD2 pins of the first CF card 41, for example, when the first CF card connector 31 adopts the embodiment of fig. 2, the 25 th and 26 th pins of the first CF card connector 31 are respectively used for connecting the CD1 and CD2 pins of the first CF card 41, when the first CF card 41 is not connected, the 25 th and 26 th pins of the first CF card connector 31 are both default high levels, when the first CF card 41 is normally connected, the 25 th and 26 th pins of the first CF card connector 31 are both low levels, and when only one of the 25 th and 26 th pins of the first CF card connector 31 is low levels, it is indicated that the first CF card 41 is in place, but is not inserted, that is, the contact failure described in this application. That is, in this embodiment, when both CD1 and CD2 of the first CF card 41 are detected to be high, D4 of the destination register in the second controller 50 is set to 0, and D6 is set to 0. When one of CD1 and CD2 of the first CF card 41 is detected to be high, D4 of the destination register in the second controller 50 is set to 1, and D6 is set to 1. When both CD1 and CD2 of the first CF card 41 are detected to be low, D4 of the destination register in the second controller 50 is set to 1, and D6 is set to 0.

The second CF card 42 is similar to the first CF card 41, for example, in the foregoing scenario, when it is detected that both CD1 and CD2 of the second CF card 42 are high, D5 of the target register in the second controller 50 may be set to 0, and D7 may be set to 0. When one of CD1 and CD2 of the second CF card 42 is detected to be high, D5 of the destination register in the second controller 50 is set to 1 and D7 is set to 1. When both CD1 and CD2 of the second CF card 42 are detected to be low, D5 of the destination register in the second controller 50 is set to 1 and D7 is set to 0.

In the embodiment of table two, when the in-place status information of the first CF card 41 is that the first CF card 41 is in place and in good contact, and the in-place status information of the second CF card 42 is that the second CF card 42 is in place and in good contact, D7 to D4 are 0011, i.e. item (1) in table two. At this time, the master-slave control instruction received by the second controller 50 is a master-slave control instruction that does not carry control content. For example, table three is a truth table for the master-slave relationship setting of the CF card of one embodiment.

A third table:

first CF card connector 31	Second CF card connector 32	D3	D2	D1	D0
						M (Master)	S (Slave device)	0	0	0	0
S (Slave device)	M (Master)	0	0	0	1
						M (Master)	S (Slave device)	0	0	1	0
M (Master)	S (Slave device)	0	0	1	1
						S (Slave device)	M (Master)	0	1	X	X
M (Master)	S (Slave device)	1	0	X	X
						M (Master)	S (Slave device)	1	1	0	0
S (Slave device)	M (Master)	1	1	0	1
						M (Master)	S (Slave device)	1	1	1	0
M (Master)	S (Slave device)	1	1	1	1

In the embodiment shown in table three, when the master-slave control instruction is a master-slave control instruction that does not carry control contents, D2=0 and D3=0 of the target register in the second controller 50. That is, whether the master-slave control instruction is the master-slave control instruction carrying the control content is represented by the numerical values of D2 and D3. D2=0 and D3=0, the second controller 50 may control the master-slave relationship of the first CF card 41 and the second CF card 42 according to the electrical signal sent by the jumper device 60, in this embodiment, the master-slave relationship of the first CF card 41 and the second CF card 42 is controlled according to the levels of D1 and D0 of the jumper device 60. In the scenario of fig. 2, the setting of the master-slave relationship for the first CF card 41 and the second CF card 42 may be implemented based on the CSEL # pins of the first CF card 41 and the second CF card 42.

In the embodiment of table two, when the in-place status information of the first CF card 41 is that the first CF card 41 is in place and in good contact, and the in-place status information of the second CF card 42 is that the second CF card 42 is not in place, D7 to D4 are 0001, i.e., (6) th entry in table two. At this time, the master-slave control instruction received by the second controller 50 is a master-slave control instruction carrying control contents, so that the second controller 50 controls the first CF card 41 as a master device and the second CF card 42 as a slave device according to the received master-slave control instruction, and in the embodiment shown in table three, the master-slave control instruction at this time may cause D3=1 and D2=0. At this time, no matter what the values of D1 and D0 are, the first CF card 41 is controlled as a master device, and the second CF card 42 is controlled as a slave device, the priority of the master-slave control instruction at this time is higher, so as to avoid the situation that the jumper device 60 sends an erroneous electric signal, because only the first CF card 41 is in place and the first CF card 41 is in good contact at this time, in principle, the first CF card 41 should be controlled as a master device, and implementation of the guarantee scheme is to avoid the worker from setting the jumper device 60 in error, which causes the first CF card 41 to be in place and in good contact, but the second CF card 42 that is not in place is a master device, so that the first CF card 41 still cannot be used. X represents 0 or 1.

Further, in an embodiment of the present invention, it is considered that when the in-place state information of the first CF card 41 is specifically that the first CF card 41 is in place and has poor contact, and meanwhile, the in-place state information of the second CF card 42 is specifically that the second CF card 42 is not in place, although the first CF card 41 cannot normally operate, since the second CF card 42 is not in place, the master-slave control instruction received by the second controller 50 may also be set as a master-slave control instruction carrying control content, so that the second controller 50 controls the first CF card 41 as a master device and the second CF card 42 as a slave device according to the received master-slave control instruction.

That is, for table two, D7 to D4 are 0101, i.e., entry (5) in table two. At this time, the master-slave control instruction received by the second controller 50 is also a master-slave control instruction carrying control contents, and in the embodiment shown in table three, the master-slave control instruction at this time may cause D3=1 and D2=0. At this time, whatever the values of D1 and D0, the first CF card 41 is controlled as a master, and the second CF card 42 is controlled as a slave.

It should be noted that, in the embodiment of table two, the cases where D7 to D4 are 1101 or 1001 are not listed, because such cases do not usually occur according to the numerical meanings of D7 to D4 described above, and such abnormal cases may occur only when the target register is damaged or due to special reasons such as interference. Of course, in some cases, such a situation may be added to table two, and when such a situation occurs, alarm information is output so that the worker can find and handle such a situation in time. Similarly, table two also does not show that D7 to D4 are 1110, 0110, 0100, 1000 and 1100, which are not usually the case, but such cases can be added to table two if necessary, and when such cases occur, alarm information is output to enable a worker to timely find and handle such cases.

In the embodiment of table two, when the in-place status information of the first CF card 41 is that the first CF card 41 is not in place, and the in-place status information of the second CF card 42 is that the second CF card 42 is in place and has good contact, D7 to D4 are 0010, i.e., (8) th entry in table two. At this time, the master-slave control instruction received by the second controller 50 is a master-slave control instruction carrying control contents, so that the second controller 50 controls the second CF card 42 as a master device and controls the first CF card 41 as a slave device according to the received master-slave control instruction, and in the embodiment shown in table three, the master-slave control instruction at this time may cause D3=0 and D2=1. At this time, no matter what the values of D1 and D0 are, the second CF card 42 is controlled as the master, and the first CF card 41 is controlled as the slave, the priority of the master-slave control instruction at this time is higher, so as to avoid the situation that the jumper 60 sends the wrong electrical signal, because only the second CF card 42 is in place at this time, and the second CF card 42 is in good contact, the second CF card 42 should be controlled as the master in principle, and the implementation of the security scheme should be ensured.

Further, in an embodiment of the present invention, when the in-place status information of the first CF card 41 is that the first CF card 41 is not in place, and the in-place status information of the second CF card 42 is that the second CF card 42 is in place and has poor contact, the master-slave control instruction received by the second controller 50 may also be a master-slave control instruction carrying control content, so that the second controller 50 controls the first CF card 41 as a slave device and the second CF card 42 as a master device according to the received master-slave control instruction.

That is, for table two, D7 to D4 are 1010, i.e., item (7) in table two. At this time, the master-slave control instruction received by the second controller 50 is also a master-slave control instruction carrying control contents, and in the embodiment shown in table three, the master-slave control instruction at this time may cause D3=0 and D2=1. At this time, regardless of the values of D1 and D0, the second CF card 42 is controlled as a master, and the first CF card 41 is controlled as a slave.

Further, in an embodiment of the present invention, when the in-place status information of the first CF card 41 is that the first CF card 41 is not in place, and the in-place status information of the second CF card 42 is that the second CF card 42 is not in place, the master-slave control instruction received by the second controller 50 is a master-slave control instruction that does not carry control content. That is, for the item (9) in the second table, where D7 to D4 are 0000, the master-slave control instruction received by the second controller 50 may be a master-slave control instruction that does not carry control content, and at this time, the staff is allowed to control the master-slave relationship between the first CF card 41 and the second CF card 42 by changing the electrical signal sent by the jumper 60.

In addition, in practical applications, for the cases of the item (2), the item (3), and the item (4) in the second table, whether the master-slave control instruction received by the second controller 50 is set as a master-slave control instruction that does not carry control content or as a master-slave control instruction that carries control content may be set according to actual needs.

It should be noted that, for example, in table three, when the master-slave control instruction is set as the master-slave control instruction not carrying the control content, both D3 and D2 should be =0, and the case that both D3 and D2=1 is still listed in table three, which is to consider that when the target register is abnormal and both D3 and D2 become 1, the master-slave control instruction is still regarded as the master-slave control instruction not carrying the control content, so as to improve the fault tolerance of the solution of the present application, and of course, when such a case occurs, a prompt message may be output to remind the relevant staff to notice the case.

In an embodiment of the present invention, the method may further include: and a display device for displaying the in-place state information of the first CF card 41 and the in-place state information of the second CF card 42.

In practical applications, the BMC may be used as a display device, for example, the current in-place status information of the first CF card 41 and the in-place status information of the second CF card 42 are displayed through a management web page of the BMC web.

In one embodiment of the present invention, the second controller 50 can be a CPLD controller, which is simple and convenient.

By applying the technical scheme provided by the embodiment of the invention, considering the situation that the position of the OCP network card is vacant, at least 2 CF cards can be usually placed at the position, the CF cards support plug and play, the storage application is very convenient, and meanwhile, the storage requirement of the server is higher and higher, so that N CF cards are arranged in the OCP slot of the server. CF card can not directly with OCP slot connection, consequently this application has set up OCP connector golden finger 10 with the OCP slot connection of server to can draw out the PCIE signal of OCP slot, recycle first controller 20 and be connected with OCP connector golden finger 10, the IDE signal is supported to the CF card, first controller 20 converts the PCIE signal into the IDE signal, thereby makes the server can utilize a N CF card to carry out data storage. And then, the connection with the N CF card connectors is realized through the N CF card connectors connected with the first controller 20. To sum up, when the scheme of this application does not need the OCP network card in the server, set up a N CF, avoided the vacancy condition of this position, and be favorable to improving the storage performance of server to the CF card supports plug-and-play, and it is also very convenient to use.

Corresponding to the above embodiments of the OCP-based expansion device, embodiments of the present invention further provide a server, which may include the OCP-based expansion device in any of the above embodiments, and a description thereof is not repeated here.

It is further noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrases "comprising one of 8230; \8230;" 8230; "does not exclude the presence of additional like elements in a process, method, article, or apparatus that comprises the element.

Those of skill would further appreciate that the various illustrative components and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both, and that the components and steps of the various examples have been described above generally in terms of their functionality in order to clearly illustrate this interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention. The principle and the implementation of the present invention are explained in the present application by using specific examples, and the above description of the embodiments is only used to help understanding the technical solution and the core idea of the present invention. It should be noted that, for those skilled in the art, it is possible to make various improvements and modifications to the present invention without departing from the principle of the present invention, and those improvements and modifications also fall within the scope of the claims of the present invention.

Claims

1. An OCP-based expansion device, comprising:

the OCP connector golden finger is connected with an OCP slot of the server;

the first controller is connected with the OCP connector golden finger and is used for converting the PCIE signals into IDE signals so as to enable the server to store data by utilizing the N CF cards;

n CF card connectors connected with the first controller;

n CF cards connected with the N CF card connectors respectively; wherein N is a positive integer; n =2; further comprising:

2. The OCP-based expansion device of claim 1, further comprising:

the second controller is further configured to: and when the received master-slave control instruction is the master-slave control instruction which does not carry the control content, controlling the master-slave relationship of the first CF card and the second CF card according to the received master-slave control instruction.

3. The OCP-based expansion device according to claim 2, wherein when the in-place status information of the first CF card is that the first CF card is in a good contact state, and meanwhile, the in-place status information of the second CF card is that the second CF card is in a good contact state, the master-slave control instruction received by the second controller is a master-slave control instruction that does not carry control content;

when the in-place state information of the first CF card is particularly that the first CF card is in place and has good contact, and meanwhile, the in-place state information of the second CF card is particularly that the second CF card is not in place, a master-slave control instruction received by the second controller is a master-slave control instruction carrying control content, so that the second controller controls the first CF card to be master equipment and the second CF card to be slave equipment according to the received master-slave control instruction;

4. The OCP-based expansion device of claim 3, further comprising: and the display device is used for displaying the in-place state information of the first CF card and the in-place state information of the second CF card.

5. The OCP-based expansion device of claim 4, wherein when the in-place status information of the first CF card is specifically that the first CF card is not in place, and meanwhile, the in-place status information of the second CF card is specifically that the second CF card is not in place, the master-slave control instruction received by the second controller is a master-slave control instruction not carrying control content;

6. The OCP-based expansion device of claim 4, wherein the second controller is a CPLD controller.

7. A server, characterized in that it comprises an OCP-based expansion device according to any one of claims 1 to 6.