US20190121770A1 - Hardware resource expansion system capable of assigning hardware addresses automatically - Google Patents
Hardware resource expansion system capable of assigning hardware addresses automatically Download PDFInfo
- Publication number
- US20190121770A1 US20190121770A1 US15/863,968 US201815863968A US2019121770A1 US 20190121770 A1 US20190121770 A1 US 20190121770A1 US 201815863968 A US201815863968 A US 201815863968A US 2019121770 A1 US2019121770 A1 US 2019121770A1
- Authority
- US
- United States
- Prior art keywords
- bus
- cables
- hardware
- system management
- coupled
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F13/00—Interconnection of, or transfer of information or other signals between, memories, input/output devices or central processing units
- G06F13/38—Information transfer, e.g. on bus
- G06F13/40—Bus structure
- G06F13/4004—Coupling between buses
- G06F13/4027—Coupling between buses using bus bridges
- G06F13/404—Coupling between buses using bus bridges with address mapping
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F13/00—Interconnection of, or transfer of information or other signals between, memories, input/output devices or central processing units
- G06F13/14—Handling requests for interconnection or transfer
- G06F13/16—Handling requests for interconnection or transfer for access to memory bus
- G06F13/1668—Details of memory controller
- G06F13/1673—Details of memory controller using buffers
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F13/00—Interconnection of, or transfer of information or other signals between, memories, input/output devices or central processing units
- G06F13/38—Information transfer, e.g. on bus
- G06F13/40—Bus structure
- G06F13/4004—Coupling between buses
- G06F13/4022—Coupling between buses using switching circuits, e.g. switching matrix, connection or expansion network
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F13/00—Interconnection of, or transfer of information or other signals between, memories, input/output devices or central processing units
- G06F13/38—Information transfer, e.g. on bus
- G06F13/40—Bus structure
- G06F13/4063—Device-to-bus coupling
- G06F13/4068—Electrical coupling
- G06F13/4081—Live connection to bus, e.g. hot-plugging
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F13/00—Interconnection of, or transfer of information or other signals between, memories, input/output devices or central processing units
- G06F13/38—Information transfer, e.g. on bus
- G06F13/42—Bus transfer protocol, e.g. handshake; Synchronisation
- G06F13/4282—Bus transfer protocol, e.g. handshake; Synchronisation on a serial bus, e.g. I2C bus, SPI bus
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2213/00—Indexing scheme relating to interconnection of, or transfer of information or other signals between, memories, input/output devices or central processing units
- G06F2213/0026—PCI express
Definitions
- This invention is related to a hardware resource expansion system, and more particularly, is related to a hardware resource expansion system capable of assigning hardware addresses automatically.
- the data center tends to arrange different types of resources into different resource pools.
- the resources may be classified as computing resource, storage resource and network resource, and different types of resources can be connected by data buses, such as Peripheral Component Interconnect Express (PCIE) buses. Consequently, the hardware design can be more flexible and extensible.
- PCIE Peripheral Component Interconnect Express
- the data center may buy some storage devices, and the server can be connected to the new storage devices through PCIE buses to meet the requirement of storage.
- the computational unit of the server usually uses one single system management bus (SMBus) to manage the devices plugged into and unplugged from the PCIE slots
- the hardware addresses for the PCIE slots should be different so the hardware devices can be controlled by the same SMBus.
- SMBus system management bus
- the pins of hardware devices or PCIE slots have to be adjusted by manually, or additional circuits have to be added. Therefore, hardware design becomes more complicate, and the burdens of labors become heavier, lowering the efficiency of the management of the datacenter.
- the hardware resource expansion system includes a server, a first set of auxiliary signal cables, a first set of PCIE transmission cables, a first hardware expansion device, and a first hot swap management device.
- the server includes a computational unit and a baseboard management controller.
- the computational unit is coupled to a host system management bus and a plurality of peripheral component interconnect express (PCIE) buses.
- PCIE peripheral component interconnect express
- the baseboard management controller is coupled to the computational unit and a plurality of board system management buses.
- the first set of auxiliary signal cables includes a first set of system management bus cables and second set of system management bus cables.
- the first set of system management bus cables are selectively coupled to the host system management bus, and the second set of system management bus cables are selectively coupled to a first board system management bus of the plurality of board system management buses.
- the first set of PCIE transmission cables are selectively coupled to a first PCIE bus of the plurality of PCIE buses.
- the first hot swap management device is coupled to the first hardware expansion device and the first set of auxiliary signal cables, and the first hot swap management device includes a first bus buffer, a first hot swap switch, and a first controller.
- the first bus buffer is coupled to the first set of system management bus cables of the first set of auxiliary signal cables.
- the first hot swap switch is coupled to the first bus buffer and the first hardware expansion device.
- the first controller is coupled to the second set of system management bus cables of the first set of auxiliary signal cables, the first bus buffer, and the first hot swap switch.
- the first controller assigns a first hardware address to the first bus buffer when the second set of system management bus cables of the first set of auxiliary signal cables is coupled to the first board system management bus.
- the computing unit controls the first hardware expansion device through the first set of system management bus cables of the first set of auxiliary signal cables according to the first hardware address.
- the hot swap management device includes a bus buffer, a hot swap switch, and a controller.
- the bus buffer is selectively coupled to a host system management bus of a server.
- the hot swap switch is coupled to the bus buffer and a hardware expansion device.
- the controller is coupled to the bus buffer and the hot swap switch, and the controller assigns a hardware address to the bus buffer when the hot swap management device is coupled to a board system management bus of the server.
- a computational unit of the server controls the hardware expansion device through the host system management bus according to the hardware address.
- FIG. 1 shows a hardware resource expansion system according to one embodiment of the present invention.
- FIG. 2 shows another usage scheme of the hardware resource expansion system in FIG. 1 .
- FIG. 1 shows a hardware resource expansion system 100 according to one embodiment of the present invention.
- the hardware resource expansion system 100 includes a server 110 , a first set of auxiliary signal cables 120 A, a first set of PCIE transmission cables 130 A, a first hardware expansion device 140 A, and a first hot swap management device 150 A.
- the server 110 includes a computational unit 112 and a baseboard management controller (BMC) 114 .
- the computational unit 112 can be a processor having computing power, including a single-cored or multi-cored processor.
- the computation unit 112 can be coupled to a host system management bus (SMBus) HS 1 and N PCIE buses P 1 to PN, where N is an integer greater than 1.
- SMBs system management bus
- the server 110 can control the hardware expansion devices coupled to the PCIE buses P 1 to PN through the host SMBus HS 1 .
- the PCIE buses P 1 to PN can be coupled to different hardware expansion devices, such as disc array and general purpose graphic processing unit (GPGPU) array.
- GPGPU general purpose graphic processing unit
- the server can use the host SMBus HS 1 to check the statuses of the hardware expansion devices to see if the connections have been properly established, the power has been turned on, or the devices are to be unplugged. Therefore, the server 110 can establish or terminate the communications connection between the hardware expansion devices and the PCIE buses P 1 to PN according to the statuses detected by the host SMBus HS 1 .
- the BMC 114 can control other devices on the board of the server 110 , such as temperature sensors and fans, for reducing the burden of the computational unit 112 and ensuring the server 110 to function properly. Since the BMC 114 is used to control many devices, the BMC 114 is usually equipped with more SMBuses. In FIG. 1 , the BMC 114 can be coupled to the computational unit 112 and M board SMBuses BS 1 to BSM, where M is an integer greater than 1.
- the server 110 can be coupled to the external hardware expansion devices through the auxiliary signal cables and PCIE transmission cables.
- the first set of auxiliary signal cables 120 and the first set of PCIE transmission cables 130 A can be selectively coupled to the server 110 , that is, the first set of auxiliary signal cables 120 and the first set of PCIE transmission cables 130 A can be plugged into or unplugged from the server 110 according to system requirements.
- the first set of auxiliary signal cables 120 A can transmit the signals required for controlling the hardware expansion devices, for example, the first set of auxiliary signal cables 120 A can include a first set of SMBus cables 120 A 1 and a second set of SMBus cables 120 A 2 .
- the first set of SMBus cables 120 A 1 can be selectively coupled to the host SMBus HS 1 as the first set of auxiliary signal cables 120 A while the second set of SMBus cables 120 A 2 can be selectively coupled to a first board SMBus BS 1 of the board SMBuses BS 1 to BSM as the first set of auxiliary signal cables 120 A.
- first set of PCIE transmission cables 130 A can be selectively coupled to a first PCIE bus P 1 of the PCIE buses P 1 to PN.
- the first set of SMBus cables 120 A 1 , the second set of SMBus cables 120 A 2 , and the first PCIE transmission cables 130 A are represented by single lines, they may include more than one signal cable, and the number of cables may be related to the type of bus and the transmission standards used by the system.
- the first set of SMBus cables 120 A 1 can include two cables: the data cable and the clock cable, required by the SMBus transmission
- the first set of PCIE transmission cables 130 A can include, for example but not limited to, four signal cables.
- the first set of auxiliary signal cables 120 A and the first set of PCIE transmission cables 130 A can be bundled together, and the connection port disposed on the server 110 can be designed to correspond to the signal cables of the first set of auxiliary signal cables 120 A and the first set of PCIE transmission cables 130 A, making the connection even easier for users. Consequently, the user only needs to plug the bundled cables into the corresponding port of the server 110 , and the first set of SMBus cables 120 A 1 will be coupled to the host SMBus HS 1 , the second set of SMBus cables 120 A 2 will be coupled to the first board SMBus BS 1 , and the first set of PCIE transmission cables 130 A will be coupled to the first PCIE bus P 1 .
- the first set of auxiliary signal cables 120 A may further include other signal cables, such as the reference clock signal cable and the reset signal cable for PCIE transmission.
- the first hardware expansion device 140 A can be used by the server 110 as an external hardware expansion device, and can provide the required hardware resource to the server 110 .
- the first hardware expansion device 140 A can be memory storage device or computation resources.
- the first hardware expansion device 140 A and the server 110 can be connected through the first hot swap management device 150 A.
- the first hot swap management device 150 A can be coupled to the first hardware expansion device 140 A and the first set of auxiliary signal cables 120 A.
- the first hot swap management device 150 A includes a first bus buffer 152 A, a first hot swap switch 154 A, and a first controller 156 A.
- the first bus buffer 152 A can be an inter-integrated circuit (I2C) bus buffer, and the first bus buffer 152 A can be assigned with a hardware address and analyze the received hardware addresses for extending the number of hardware devices coupled to the I2C bus.
- the first bus buffer 152 A can be coupled to the first set of SMBus cables 120 A 1 of the first set of auxiliary signal cables 120 A.
- the first hot swap switch 154 A can be coupled to the first bus buffer 152 A and the first hardware expansion device 140 A.
- the first controller 156 A can be coupled to the second set of system management bus cables 120 A 2 of the first set of auxiliary signal cables 120 A, the first bus buffer 152 A, and the first hot swap switch 154 A.
- the first controller 156 A can send a query to the BMC 114 through the second set of SMBus cables 120 A 2 for the available hardware addresses, and assign a first hardware address to the first bus buffer 152 A according to the available hardware addresses provided by the BMC 114 . Consequently, the computational unit 112 can control the first hardware expansion device 140 through the first set of SMBus cables 120 A 1 of the first set of auxiliary signal cables 120 A according to the first hardware address.
- the first hot swap management device 150 A can be disposed on the same baseboard B 1 as the first hardware expansion device 140 A, and the first hot swap management device 150 A can determine the connection status between the transmission cables and the buses according to pull up resistors disposed at the connection portions of the buses.
- the first hardware expansion device 140 A can transmit its status parameters to the computational unit 112 through the first set of SMBus 120 A 1 of the first set of auxiliary signal cables 120 A, so the server 110 can be aware of the status of the first hardware expansion device 140 A. For example, after connecting the first hardware expansion device 140 and the serve 110 with the first set of auxiliary signal cables 120 A and the first set of PCIE transmission cables 130 A, the user can push a notification button of the first hardware expansion device 140 .
- the first hardware expansion device 140 can transmit the notification signal to the computational unit 112 through the first bus buffer 152 A and the first set of SMBus cables 120 A 1 (or other predefined signal cables), and the computational unit 112 will establish the communications connection between the first set of PCIE transmission cables 130 A and the first PCIE bus P 1 accordingly.
- the user can push a removal notification button.
- the first hardware expansion device 140 can transmit the removal notification signal to the computational unit 112 through the first bus buffer 152 A and the first set of SMBus cables 120 A 1 , and the computational unit 112 will terminate the communications connection between the first set of PCIE transmission cables 130 A and the first PCIE bus P 1 accordingly.
- the server 110 can use the hardware resource provided by the first hardware expansion device 140 , and the first hardware expansion device 140 can be hot plugged in or unplugged when the server 110 remains functioning.
- FIG. 2 shows another usage scheme of the hardware resource expansion system 100 .
- the hardware resource expansion system 100 can further include a second set of auxiliary signal cables 120 B, a second set of PCIE transmission cables 130 B, a second hardware expansion device 140 B, and a second hot swap management device 150 B.
- the second set of auxiliary signal cables 120 B may include a first set of SMBus cables 120 B 1 and a second set of SMBus cables 120 B 2 .
- the first set of SMBus cables 120 B 1 can be selectively coupled to the host system management bus HS 1
- the second set of SMBus cables can be selectively coupled to a second board SMBus BS 2
- the second set of PCIE transmission cables 130 B can be selectively coupled to the second PCIE bus P 2 .
- the second hot swap management device 150 B is coupled to the second hardware expansion device 140 B and the second set of auxiliary signal cables 120 B.
- the second hot swap management device 150 B includes a second bus buffer 152 B, a second hot swap switch 154 B, and a second controller 156 B.
- the second bus buffer 152 B can be coupled to the first set of SMBus cables 120 B 1 of the second set of auxiliary signal cables 120 B, the second hot swap switch 154 B can be coupled to the second bus buffer 152 B and the second hardware expansion device 140 B.
- the second controller 156 B can be coupled to the second set of SMBus cables 120 B 2 of the second set of auxiliary signal cables 120 B, the second bus buffer 152 B, and the second hot swap switch 154 B.
- the controller 156 B can assign a second hardware address to the second bus buffer 152 B.
- the second controller 156 B can obtain the available hardware addresses that haven't been used by other devices from the BMC 114 through the second set of SMBus cables 120 B 2 and the second board SMBus BS 2 , so the second controller 156 B can assign the second hardware address accordingly. Consequently, it can be ensured that the second hardware address would be different from the first hardware address, allowing the computational unit 112 to control the first hardware expansion device 140 A and the second hardware expansion device 140 B through the host SMBus HS 1 without setting the hardware addresses manually. Consequently, not only the operations can be simplified, but the efficiency can also be improved.
- the hardware resource expansion systems and the hot swap management devices provided by the embodiments of the present invention can assign the corresponding hardware addresses when the hardware expansion devices are coupled to the servers, ensuring the server can control the hardware expansion devices individually and effectively to use the hardware resources.
- the hardware resource expansion systems and the hot swap management devices can assign the hardware addresses without manual setting; therefore, not only the operations can be simplified, but the efficiency can also be improved.
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Hardware Design (AREA)
- Mathematical Physics (AREA)
- Bus Control (AREA)
Abstract
Description
- This invention is related to a hardware resource expansion system, and more particularly, is related to a hardware resource expansion system capable of assigning hardware addresses automatically.
- As cloud computing being applied to more and more fields, the data center tends to arrange different types of resources into different resource pools. For example, the resources may be classified as computing resource, storage resource and network resource, and different types of resources can be connected by data buses, such as Peripheral Component Interconnect Express (PCIE) buses. Consequently, the hardware design can be more flexible and extensible.
- For example, when the server requires more storage space, the data center may buy some storage devices, and the server can be connected to the new storage devices through PCIE buses to meet the requirement of storage. However, in prior art, since the computational unit of the server usually uses one single system management bus (SMBus) to manage the devices plugged into and unplugged from the PCIE slots, the hardware addresses for the PCIE slots should be different so the hardware devices can be controlled by the same SMBus. In practical, to set up hardware addresses for the PCIE slots, the pins of hardware devices or PCIE slots have to be adjusted by manually, or additional circuits have to be added. Therefore, hardware design becomes more complicate, and the burdens of labors become heavier, lowering the efficiency of the management of the datacenter.
- One embodiment of the present invention discloses a hardware resource expansion system. The hardware resource expansion system includes a server, a first set of auxiliary signal cables, a first set of PCIE transmission cables, a first hardware expansion device, and a first hot swap management device.
- The server includes a computational unit and a baseboard management controller. The computational unit is coupled to a host system management bus and a plurality of peripheral component interconnect express (PCIE) buses. The baseboard management controller is coupled to the computational unit and a plurality of board system management buses.
- The first set of auxiliary signal cables includes a first set of system management bus cables and second set of system management bus cables. The first set of system management bus cables are selectively coupled to the host system management bus, and the second set of system management bus cables are selectively coupled to a first board system management bus of the plurality of board system management buses.
- The first set of PCIE transmission cables are selectively coupled to a first PCIE bus of the plurality of PCIE buses.
- The first hot swap management device is coupled to the first hardware expansion device and the first set of auxiliary signal cables, and the first hot swap management device includes a first bus buffer, a first hot swap switch, and a first controller.
- The first bus buffer is coupled to the first set of system management bus cables of the first set of auxiliary signal cables. The first hot swap switch is coupled to the first bus buffer and the first hardware expansion device. The first controller is coupled to the second set of system management bus cables of the first set of auxiliary signal cables, the first bus buffer, and the first hot swap switch. The first controller assigns a first hardware address to the first bus buffer when the second set of system management bus cables of the first set of auxiliary signal cables is coupled to the first board system management bus.
- The computing unit controls the first hardware expansion device through the first set of system management bus cables of the first set of auxiliary signal cables according to the first hardware address.
- Another embodiment of the present invention discloses a hot swap management device. The hot swap management device includes a bus buffer, a hot swap switch, and a controller.
- The bus buffer is selectively coupled to a host system management bus of a server. The hot swap switch is coupled to the bus buffer and a hardware expansion device. The controller is coupled to the bus buffer and the hot swap switch, and the controller assigns a hardware address to the bus buffer when the hot swap management device is coupled to a board system management bus of the server.
- A computational unit of the server controls the hardware expansion device through the host system management bus according to the hardware address.
- These and other objectives of the present invention will no doubt become obvious to those of ordinary skill in the art after reading the following detailed description of the preferred embodiment that is illustrated in the various figures and drawings.
-
FIG. 1 shows a hardware resource expansion system according to one embodiment of the present invention. -
FIG. 2 shows another usage scheme of the hardware resource expansion system inFIG. 1 . -
FIG. 1 shows a hardwareresource expansion system 100 according to one embodiment of the present invention. The hardwareresource expansion system 100 includes aserver 110, a first set ofauxiliary signal cables 120A, a first set ofPCIE transmission cables 130A, a firsthardware expansion device 140A, and a first hotswap management device 150A. - The
server 110 includes acomputational unit 112 and a baseboard management controller (BMC) 114. Thecomputational unit 112 can be a processor having computing power, including a single-cored or multi-cored processor. Thecomputation unit 112 can be coupled to a host system management bus (SMBus) HS1 and N PCIE buses P1 to PN, where N is an integer greater than 1. Theserver 110 can control the hardware expansion devices coupled to the PCIE buses P1 to PN through the host SMBus HS1. For example, the PCIE buses P1 to PN can be coupled to different hardware expansion devices, such as disc array and general purpose graphic processing unit (GPGPU) array. When the hardware expansion devices are coupled to the PCIE buses P1 to PN, the server can use the host SMBus HS1 to check the statuses of the hardware expansion devices to see if the connections have been properly established, the power has been turned on, or the devices are to be unplugged. Therefore, theserver 110 can establish or terminate the communications connection between the hardware expansion devices and the PCIE buses P1 to PN according to the statuses detected by the host SMBus HS1. - The BMC 114 can control other devices on the board of the
server 110, such as temperature sensors and fans, for reducing the burden of thecomputational unit 112 and ensuring theserver 110 to function properly. Since the BMC 114 is used to control many devices, the BMC 114 is usually equipped with more SMBuses. InFIG. 1 , the BMC 114 can be coupled to thecomputational unit 112 and M board SMBuses BS1 to BSM, where M is an integer greater than 1. - In some embodiments, the
server 110 can be coupled to the external hardware expansion devices through the auxiliary signal cables and PCIE transmission cables. For example, inFIG. 1 , the first set of auxiliary signal cables 120 and the first set ofPCIE transmission cables 130A can be selectively coupled to theserver 110, that is, the first set of auxiliary signal cables 120 and the first set ofPCIE transmission cables 130A can be plugged into or unplugged from theserver 110 according to system requirements. - The first set of
auxiliary signal cables 120A can transmit the signals required for controlling the hardware expansion devices, for example, the first set ofauxiliary signal cables 120A can include a first set of SMBus cables 120A1 and a second set of SMBus cables 120A2. The first set of SMBus cables 120A1 can be selectively coupled to the host SMBus HS1 as the first set ofauxiliary signal cables 120A while the second set of SMBus cables 120A2 can be selectively coupled to a first board SMBus BS1 of the board SMBuses BS1 to BSM as the first set ofauxiliary signal cables 120A. - In addition, the first set of
PCIE transmission cables 130A can be selectively coupled to a first PCIE bus P1 of the PCIE buses P1 to PN. - In
FIG. 1 , although the first set of SMBus cables 120A1, the second set of SMBus cables 120A2, and the firstPCIE transmission cables 130A are represented by single lines, they may include more than one signal cable, and the number of cables may be related to the type of bus and the transmission standards used by the system. For example, the first set of SMBus cables 120A1 can include two cables: the data cable and the clock cable, required by the SMBus transmission, and the first set ofPCIE transmission cables 130A can include, for example but not limited to, four signal cables. - In some embodiments, the first set of
auxiliary signal cables 120A and the first set ofPCIE transmission cables 130A can be bundled together, and the connection port disposed on theserver 110 can be designed to correspond to the signal cables of the first set ofauxiliary signal cables 120A and the first set ofPCIE transmission cables 130A, making the connection even easier for users. Consequently, the user only needs to plug the bundled cables into the corresponding port of theserver 110, and the first set of SMBus cables 120A1 will be coupled to the host SMBus HS1, the second set of SMBus cables 120A2 will be coupled to the first board SMBus BS1, and the first set ofPCIE transmission cables 130A will be coupled to the first PCIE bus P1. - In some embodiments, the first set of
auxiliary signal cables 120A may further include other signal cables, such as the reference clock signal cable and the reset signal cable for PCIE transmission. - The first
hardware expansion device 140A can be used by theserver 110 as an external hardware expansion device, and can provide the required hardware resource to theserver 110. For example, the firsthardware expansion device 140A can be memory storage device or computation resources. To allow the firsthardware expansion device 140A to be plugged in or unplugged when theserver 110 is under operation, the firsthardware expansion device 140A and theserver 110 can be connected through the first hotswap management device 150A. - The first hot
swap management device 150A can be coupled to the firsthardware expansion device 140A and the first set ofauxiliary signal cables 120A. The first hotswap management device 150A includes afirst bus buffer 152A, a firsthot swap switch 154A, and afirst controller 156A. - The
first bus buffer 152A can be an inter-integrated circuit (I2C) bus buffer, and thefirst bus buffer 152A can be assigned with a hardware address and analyze the received hardware addresses for extending the number of hardware devices coupled to the I2C bus. Thefirst bus buffer 152A can be coupled to the first set of SMBus cables 120A1 of the first set ofauxiliary signal cables 120A. - The first
hot swap switch 154A can be coupled to thefirst bus buffer 152A and the firsthardware expansion device 140A. Thefirst controller 156A can be coupled to the second set of system management bus cables 120A2 of the first set ofauxiliary signal cables 120A, thefirst bus buffer 152A, and the firsthot swap switch 154A. - When the second set of system management bus cables 120A2 of the first set of
auxiliary signal cables 120A is coupled to the first board system management bus BS1, thefirst controller 156A can send a query to theBMC 114 through the second set of SMBus cables 120A2 for the available hardware addresses, and assign a first hardware address to thefirst bus buffer 152A according to the available hardware addresses provided by the BMC114. Consequently, thecomputational unit 112 can control the first hardware expansion device 140 through the first set of SMBus cables 120A1 of the first set ofauxiliary signal cables 120A according to the first hardware address. Furthermore, the first hotswap management device 150A can be disposed on the same baseboard B1 as the firsthardware expansion device 140A, and the first hotswap management device 150A can determine the connection status between the transmission cables and the buses according to pull up resistors disposed at the connection portions of the buses. - In some embodiments, the first
hardware expansion device 140A can transmit its status parameters to thecomputational unit 112 through the first set of SMBus 120A1 of the first set ofauxiliary signal cables 120A, so theserver 110 can be aware of the status of the firsthardware expansion device 140A. For example, after connecting the first hardware expansion device 140 and the serve 110 with the first set ofauxiliary signal cables 120A and the first set ofPCIE transmission cables 130A, the user can push a notification button of the first hardware expansion device 140. In this case, the first hardware expansion device 140 can transmit the notification signal to thecomputational unit 112 through thefirst bus buffer 152A and the first set of SMBus cables 120A1 (or other predefined signal cables), and thecomputational unit 112 will establish the communications connection between the first set ofPCIE transmission cables 130A and the first PCIE bus P1 accordingly. - Also, if the user wants to remove the first hardware expansion device 140, the user can push a removal notification button. In this case, the first hardware expansion device 140 can transmit the removal notification signal to the
computational unit 112 through thefirst bus buffer 152A and the first set of SMBus cables 120A1, and thecomputational unit 112 will terminate the communications connection between the first set ofPCIE transmission cables 130A and the first PCIE bus P1 accordingly. - Consequently, the
server 110 can use the hardware resource provided by the first hardware expansion device 140, and the first hardware expansion device 140 can be hot plugged in or unplugged when theserver 110 remains functioning. -
FIG. 2 shows another usage scheme of the hardwareresource expansion system 100. InFIG. 2 , the hardwareresource expansion system 100 can further include a second set ofauxiliary signal cables 120B, a second set ofPCIE transmission cables 130B, a secondhardware expansion device 140B, and a second hotswap management device 150B. - The second set of
auxiliary signal cables 120B may include a first set of SMBus cables 120B1 and a second set of SMBus cables 120B2. The first set of SMBus cables 120B1 can be selectively coupled to the host system management bus HS1, the second set of SMBus cables can be selectively coupled to a second board SMBus BS2, and the second set ofPCIE transmission cables 130B can be selectively coupled to the second PCIE bus P2. - The second hot
swap management device 150B is coupled to the secondhardware expansion device 140B and the second set ofauxiliary signal cables 120B. The second hotswap management device 150B includes asecond bus buffer 152B, a secondhot swap switch 154B, and asecond controller 156B. - The
second bus buffer 152B can be coupled to the first set of SMBus cables 120B1 of the second set ofauxiliary signal cables 120B, the secondhot swap switch 154B can be coupled to thesecond bus buffer 152B and the secondhardware expansion device 140B. Thesecond controller 156B can be coupled to the second set of SMBus cables 120B2 of the second set ofauxiliary signal cables 120B, thesecond bus buffer 152B, and the secondhot swap switch 154B. - When the second set of system management bus cables 120B2 of the second set of
auxiliary signal cables 120B is coupled to the second board SMBus BS2, thecontroller 156B can assign a second hardware address to thesecond bus buffer 152B. - In some embodiments, the
second controller 156B can obtain the available hardware addresses that haven't been used by other devices from theBMC 114 through the second set of SMBus cables 120B2 and the second board SMBus BS2, so thesecond controller 156B can assign the second hardware address accordingly. Consequently, it can be ensured that the second hardware address would be different from the first hardware address, allowing thecomputational unit 112 to control the firsthardware expansion device 140A and the secondhardware expansion device 140B through the host SMBus HS1 without setting the hardware addresses manually. Consequently, not only the operations can be simplified, but the efficiency can also be improved. - In summary, the hardware resource expansion systems and the hot swap management devices provided by the embodiments of the present invention can assign the corresponding hardware addresses when the hardware expansion devices are coupled to the servers, ensuring the server can control the hardware expansion devices individually and effectively to use the hardware resources. In other words, the hardware resource expansion systems and the hot swap management devices can assign the hardware addresses without manual setting; therefore, not only the operations can be simplified, but the efficiency can also be improved.
- Those skilled in the art will readily observe that numerous modifications and alterations of the device and method may be made while retaining the teachings of the invention. Accordingly, the above disclosure should be construed as limited only by the metes and bounds of the appended claims.
Claims (10)
Applications Claiming Priority (3)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711000147 | 2017-10-24 | ||
CN201711000147.0 | 2017-10-24 | ||
CN201711000147.0A CN109697179B (en) | 2017-10-24 | 2017-10-24 | Hardware resource expansion system and hot plug management device |
Publications (2)
Publication Number | Publication Date |
---|---|
US20190121770A1 true US20190121770A1 (en) | 2019-04-25 |
US10289593B1 US10289593B1 (en) | 2019-05-14 |
Family
ID=66170576
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US15/863,968 Active US10289593B1 (en) | 2017-10-24 | 2018-01-07 | Hardware resource expansion system capable of assigning hardware addresses automatically |
Country Status (2)
Country | Link |
---|---|
US (1) | US10289593B1 (en) |
CN (1) | CN109697179B (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US10592462B2 (en) * | 2018-06-19 | 2020-03-17 | Quanta Computer Inc. | Cable detection |
CN111241025A (en) * | 2020-03-09 | 2020-06-05 | 杭州富阳浮想电脑有限公司 | Hot plug device for mobile hardware of server |
US20210311889A1 (en) * | 2020-02-20 | 2021-10-07 | Silicon Motion, Inc. | Memory device and associated flash memory controller |
Family Cites Families (20)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5898848A (en) * | 1996-10-21 | 1999-04-27 | Advanced Micro Devices, Inc. | Inter-chip bus structure for moving multiple isochronous data streams between integrated circuits |
US6038680A (en) * | 1996-12-11 | 2000-03-14 | Compaq Computer Corporation | Failover memory for a computer system |
US6178469B1 (en) * | 1998-06-30 | 2001-01-23 | Compaq Computer Corporation | Enabling access to a selected one of two detected same type peripheral devices connected to separate peripheral slots in a computer |
US6505305B1 (en) * | 1998-07-16 | 2003-01-07 | Compaq Information Technologies Group, L.P. | Fail-over of multiple memory blocks in multiple memory modules in computer system |
US6571360B1 (en) * | 1999-10-19 | 2003-05-27 | Sun Microsystems, Inc. | Cage for dynamic attach testing of I/O boards |
EP1193918B1 (en) * | 2000-09-20 | 2007-08-22 | Broadcom Corporation | Switch assembly having multiple blades in a chassis |
US6948021B2 (en) * | 2000-11-16 | 2005-09-20 | Racemi Systems | Cluster component network appliance system and method for enhancing fault tolerance and hot-swapping |
US6760869B2 (en) * | 2001-06-29 | 2004-07-06 | Intel Corporation | Reporting hard disk drive failure |
US7000053B2 (en) * | 2001-07-26 | 2006-02-14 | Sun Microsystems, Inc. | Computer system having a hot swappable hot swap controller |
US7685348B2 (en) * | 2001-08-07 | 2010-03-23 | Hewlett-Packard Development Company, L.P. | Dedicated server management card with hot swap functionality |
US6901531B2 (en) * | 2001-11-30 | 2005-05-31 | Sun Microsystems, Inc. | Automatic system control failover |
DE50206073D1 (en) * | 2002-04-30 | 2006-05-11 | Haslerrail Ag Bern | Device arrangement and method for assigning address ranges to modules connected to a VME bus |
US8346912B2 (en) * | 2007-10-15 | 2013-01-01 | Dell Products, Lp | System and method of emulating a network controller within an information handling system |
WO2011068517A1 (en) * | 2009-12-04 | 2011-06-09 | Hewlett-Packard Development Company, L.P. | Circuitry for hot-swappable circuit boards |
WO2013171832A1 (en) * | 2012-05-14 | 2013-11-21 | 富士通株式会社 | Information processing device, information processing method and program |
US9456515B2 (en) * | 2013-01-23 | 2016-09-27 | Seagate Technology Llc | Storage enclosure with independent storage device drawers |
US9582453B2 (en) * | 2013-08-15 | 2017-02-28 | Western Digital Technologies, Inc. | I/O card architecture based on a common controller |
US9582373B2 (en) * | 2014-03-31 | 2017-02-28 | Vmware, Inc. | Methods and systems to hot-swap a virtual machine |
CN106815163B (en) * | 2015-12-02 | 2019-10-18 | 上海兆芯集成电路有限公司 | Have the System on Chip/SoC and its PCI-E root port controller of warm connection function |
CN107273245B (en) * | 2017-06-12 | 2020-05-19 | 英业达科技有限公司 | Operation device and operation method |
-
2017
- 2017-10-24 CN CN201711000147.0A patent/CN109697179B/en active Active
-
2018
- 2018-01-07 US US15/863,968 patent/US10289593B1/en active Active
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US10592462B2 (en) * | 2018-06-19 | 2020-03-17 | Quanta Computer Inc. | Cable detection |
US20210311889A1 (en) * | 2020-02-20 | 2021-10-07 | Silicon Motion, Inc. | Memory device and associated flash memory controller |
CN111241025A (en) * | 2020-03-09 | 2020-06-05 | 杭州富阳浮想电脑有限公司 | Hot plug device for mobile hardware of server |
Also Published As
Publication number | Publication date |
---|---|
US10289593B1 (en) | 2019-05-14 |
CN109697179B (en) | 2022-06-24 |
CN109697179A (en) | 2019-04-30 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US9858238B2 (en) | Dual mode USB and serial console port | |
US10289593B1 (en) | Hardware resource expansion system capable of assigning hardware addresses automatically | |
US11199890B2 (en) | Peripheral device expansion card system | |
US9804980B2 (en) | System management through direct communication between system management controllers | |
JP2013541742A (en) | Dynamic multilink editing partitioning system and method | |
US10499534B2 (en) | System and method for wireless rack management controller communication | |
CN107391419B (en) | Support general sequence busbar concentrator of many host computers and automobile-used host computer | |
US9940275B2 (en) | System and method to avoid SMBus address conflicts via a baseboard management controller | |
US10614011B2 (en) | Apparatus, method, and electronic device for implementing solid-state drive data interaction | |
US9411771B2 (en) | Server system for switching master and slave devices | |
CN105703935A (en) | Server system with function of automatic switching of shared network | |
US20170309570A1 (en) | Reconfigurable repeater system | |
EP3637270A1 (en) | External electrical connector and computer system | |
US20120005348A1 (en) | Managing Shared Resources In A Multi-Computer System With Failover Support | |
US10360167B1 (en) | Systems and methods for using a bus exchange switch to control processor affinity | |
US10762031B2 (en) | System and method for setting equalization for communication between a processor and a device | |
CN109697180B (en) | Hardware resource expansion system | |
US20050160207A1 (en) | Computing apparatus including a hardware management add-on card | |
TWI658367B (en) | Hardware resource expansion system | |
TWI658366B (en) | Hardware resource expansion system and hot swap management device | |
US20160366024A1 (en) | Method and associated apparatus for managing a storage system | |
CN112732627B (en) | OCP device and server | |
JP2021096855A (en) | Interface device, computer system, and method |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
AS | Assignment |
Owner name: INVENTEC CORPORATION, TAIWAN Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNOR:CHANG, PO-CHUNG;REEL/FRAME:044553/0584 Effective date: 20180103 Owner name: INVENTEC (PUDONG) TECHNOLOGY CORP., CHINA Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNOR:CHANG, PO-CHUNG;REEL/FRAME:044553/0584 Effective date: 20180103 |
|
FEPP | Fee payment procedure |
Free format text: ENTITY STATUS SET TO UNDISCOUNTED (ORIGINAL EVENT CODE: BIG.); ENTITY STATUS OF PATENT OWNER: LARGE ENTITY |
|
STCF | Information on status: patent grant |
Free format text: PATENTED CASE |
|
MAFP | Maintenance fee payment |
Free format text: PAYMENT OF MAINTENANCE FEE, 4TH YEAR, LARGE ENTITY (ORIGINAL EVENT CODE: M1551); ENTITY STATUS OF PATENT OWNER: LARGE ENTITY Year of fee payment: 4 |