WO2017058143A1

WO2017058143A1 - Protocol conversion for servers and chassis

Info

Publication number: WO2017058143A1
Application number: PCT/US2015/052652
Authority: WO
Inventors: Peter Hansen; Han Wang; Vincent W. Michna
Original assignee: Hewlett Packard Enterprise Development Lp
Priority date: 2015-09-28
Filing date: 2015-09-28
Publication date: 2017-04-06

Abstract

In example implementations, an apparatus includes a processor and a non-transitory computer-readable storage medium. The non-transitory computer-readable storage medium includes instructions that, when executed by the processor, cause the processor to identify a protocol used to send a data packet via a protocol detector. The instructions also cause the processor to send a switching command to a mode switcher when a mismatch of the protocol used to send the data packet between a server and a chassis occurs. The instructions also cause the processor to enable a protocol conversion in response to the switching command to convert the data packet into a common protocol between the server and the chassis.

Description

PROTOCOL CONVERSION FOR SERVERS AND CHASSIS

BACKGROUND

[0001] Servers are used for a variety of different applications and to manage networks over the Internet, such as, hosting a website, controlling data traffic, computing clusters, and the like. Servers have evolved from stand-alone machines into more compact blade servers that share a common chassis. The blade servers share a common equipment on the chassis, such as, a power supply, a cooling fan, and the like. The transformation of the servers to the compact blade servers have helped to save real estate and space with the proliferation of servers required to handle the constantly expanding size of Internet traffic.

BRIEF DESCRIPTION OF THE DRAWINGS

[0002] FIG. 1 is a block diagram of an example server and an example chassis of the present disclosure;

[0003] FIG. 2 is a block diagram of an example server management abstraction layer and an example chassis management abstraction layer of the present disclosure;

[0004] FIG. 3 is a block diagram of an example of the apparatus of the present disclosure;

[0005] FIG. 4 is a flow diagram of an example method for performing a protocol conversion by a chassis;

[0006] FIG. 5 is a flow diagram of an example method for performing a protocol conversion by a server; and

[0007] FIG. 6 is a block diagram of an example non-transitory computer readable storage medium storing instructions for performing a protocol conversion by the chassis.

DETAILED DESCRIPTION

[0008] The present disclosure broadly discloses a management abstraction layer that can be installed on a server and/or a chassis for performing protocol conversion. As Internet traffic has grown, the amount of servers deployed has also grown. The size of servers has been reduced with the use of blade servers to reduce the amount of real estate and space occupied by the servers to handle and manage the Internet traffic.

[0009] A blade server includes a tray that is inserted into a chassis. A plurality of blade servers can be fitted into a single chassis and share common equipment, such as, a power supply, a cooling fan, and the like. The chassis performs routing and control functions for data being sent to and from the blade servers.

[0010] Occasionally, the blade servers and the chassis may be upgraded with new infrastructures and protocols. The blade servers may be upgraded at different times than the chassis leading to a compatibility issue. For example, the blade server may have a new protocol and the chassis may have an old protocol or the blade server may have the old protocol and the chassis may have the new protocol. Alternatively, the chassis may include a mixture of blade servers having the new protocol and the old protocol.

[0011 ] The present disclosure provides a management abstraction layer that can be installed on the blade server or the chassis. The management abstraction layer can provide conversion among different protocols to ensure forward and backward compatibility between the blade servers and the chassis. The management abstraction layer may be implemented as an additional component on an interface board of the server or coupled to the main mother board of the chassis.

[0012] FIG. 1 illustrates a block diagram of an example system 100 of the present disclosure. The system 100 may include a chassis 102 and a plurality of servers 108-1 to 108-n (herein also referred to individually as server 108 or collectively as servers 108) and a plurality of servers 1 10-1 to 1 10-n (herein also referred to individually as server 1 10 or collectively as servers 1 10). In one example, the servers 108 may have the latest, newest, or current protocol version and the servers 1 10 may have an older or outdated protocol version. The chassis 102 may include the latest or current protocol version.

[0013] It should be noted that although FIG. 1 illustrates an example combination of the chassis 102 and the servers 108 and 1 10, it should be noted that the present disclosure may be applied to other combinations of servers and chassis. For example, other combinations may include a chassis 102 having an older protocol version comprising all servers 108 with the latest protocol version or a chassis 102 having a latest protocol version comprising all servers 1 10 with the older protocol version. In other words, the present disclosure may be implemented on any combination that has a compatibility issue between a server 108 or 1 10 and a chassis 102.

[0014] In one example, the chassis 102 may include a chassis management abstraction layer 104 and a chassis management core 106. The chassis management abstraction layer 104 is discussed in further detail below. The chassis management core 106 may include a processor and a non-transitory computer readable storage medium storing instructions for performing the control and management of the servers 108 and 1 10. The chassis 102 may also include additional components (e.g., a power supply, cooling fan, input/output interfaces, and the like) that are not shown.

[0015] In one example, the servers 108 and 1 10 may each include a baseboard management controller (BMC) 1 12. The BMC 1 12 may be implemented as a processor and a non-transitory computer readable medium including instructions for communicating with the chassis 102. The instructions may include a protocol version used to execute the communications with the chassis 102.

[0016] In one example, the servers 108 may also each include a server management abstraction layer 1 16. The server management abstraction layer 1 16 may be implemented as a hardware device or apparatus that includes a processor and non-transitory computer readable medium that are coupled to an interface board of the server 108. The server management abstraction layer 1 16 is discussed in further detail below.

[0017] FIG. 2 illustrates a block diagram of an example of the server management abstraction layer 1 16 and the chassis management abstraction layer 104 of the present disclosure. In one example, the chassis management abstraction layer 104 may include a mode controller 210, a back-end protocol detector 212 (broadly a protocol detector), a chassis channel mode switcher 214 (broadly a mode switcher), and a protocol conversion 216. The mode controller 210, the back-end protocol detector 212, the chassis channel mode switcher 214 and the protocol conversion 216 may be implemented in hardware, e.g., a processor and a computer readable storage medium storing instructions to perform various functions.

[0018] In one implementation, the back-end protocol detector 212 may detect a protocol version used by a server 1 10 to send a data packet. If the protocol version used by the server 1 10 does not match the protocol version used by the chassis 102, then a mismatch of the protocol versions has occurred. The back- end protocol detector 212 may send a control signal to the mode controller 210 indicating that the mismatch has occurred.

[0019] The mode controller 210 may then send a control signal to the chassis channel mode switcher 214 to initiate a protocol conversion mode. The chassis channel mode switcher 214 may then divert the data packet to the protocol conversion 216.

[0020] In one implementation, the protocol conversion 216 may convert the data packet into a protocol that is the same as the protocol used by the chassis 102. In one example, the conversion may occur in a layer 1 (e.g., a physical layer), a layer 2 (e.g., a data link layer) or a layer 3 (e.g., a network layer), or any combination thereof, of an Open Systems Interconnect (OSI) model. For example, the conversion may change how the data packet is addressed, formatted, and the like.

[0021 ] In one example, the server management abstraction layer 1 16 may include a front-end protocol detector 202 (broadly a protocol detector), a mode controller 204, a server channel mode switcher 206 (broadly a mode switcher), and a protocol conversion 208. The server management abstraction layer 1 16 may operate similar to the chassis management abstraction layer 104. The front-end protocol detector 202, the mode controller 204, the server channel mode switcher 206, and the protocol conversion 208 may be implemented in hardware, e.g., a processor and a computer readable storage medium storing instructions to perform various functions.

[0022] For example, the front-end protocol detector 202 may detect a protocol version used by a chassis 102 to send a data packet. If the protocol version used by the chassis 102 does not match the protocol version used by the server 108, then a mismatch of the protocol versions has occurred. The front-end protocol detector 202 may send a control signal to the mode controller 204 indicating that the mismatch has occurred.

[0023] The mode controller 204 may then send a control signal to the server channel mode switcher 206 to initiate a protocol conversion mode. The server channel mode switcher 206 may then divert the data packet to the protocol conversion 208.

[0024] In one implementation, the protocol conversion 208 may convert the data packet into a protocol that is the same as the protocol used by the server 108. In one example, the conversion may occur in a layer 1 (e.g., a physical layer), a layer 2 (e.g., a data link layer) or a layer 3 (e.g., a network layer), or any combination thereof, of an Open Systems Interconnect (OSI) model. For example, the conversion may change how the data packet is addressed, formatted, and the like.

[0025] In one example, if no mismatch occurs, then the data packet may simply pass through the server channel mode switcher 206 or the chassis channel mode switcher 214. For example, a server 108 with a latest protocol version may be installed on a chassis 102 also having the latest protocol version. In one embodiment, the mode controllers 204 and 210 may be in communication via a control signal 220. Since the protocol versions match between the server 108 and the chassis 102, the data packet may simply pass through the server channel mode switcher 206 and the chassis channel mode switcher 214. In other words, the data packet can by-pass the protocol conversion 216.

[0026] FIG. 3 illustrates a block diagram of an example of an apparatus 300 of the present disclosure. The apparatus 300 may be a hardware or device representation of the server management abstraction layer 1 16 or the chassis management abstraction layer 104.

[0027] In one example, the apparatus 300 may include an input/output (I/O) interface 302. The I/O interface 302 may allow for connections to an external device for programming or configuring parameters of the apparatus 300. For example, the I/O interface 302 may allow the proper protocol conversion methods to be stored to perform the protocol conversions described herein, configuring connections (e.g., a pin, a general purpose input/output (GPIO), an interrupt request line (IRQ), a serial peripheral interface (SPI) bus, Ethernet connections, and the like).

[0028] In one example, the apparatus 300 may include a processor 304. The processor 304 may be a central processing unit (CPU), an application specific integrated controller (ASIC), a micro controller, and the like. The processor 304 may be in communication with the I/O interface 302 and a non- transitory computer readable storage medium 306. The processor 304 may execute the instructions stored in the non-transitory computer readable storage medium 306.

[0029] In one example, the non-transitory computer readable storage medium 306 may include instructions 308, 310, and 312. The instructions 308 include instructions to identify a protocol used to send a data packet via a protocol detector (e.g., the front-end protocol detector 202 or the back-end protocol detector 212). The instructions 310 include instructions to send a switching command to a mode switcher (e.g., the server channel mode switcher 206 or the chassis channel mode switcher 214) when a mismatch of the protocol used to send the data packet between a server and a chassis occurs. The instructions 312 include instructions to enable a protocol conversion (e.g., the protocol conversion 208 or the protocol conversion 216) in response to the switching command to convert the data packet into a common protocol between the server and the chassis.

[0030] In one implementation, the apparatus 300 may be coupled to the tray of a server 108 for a server management abstraction layer 1 16 implementation. The apparatus 300 may be communicatively coupled to the BMC 1 12 of the server 108. In another implementation, the apparatus 300 may be coupled to the chassis management core 106, for example, to a mother board of the chassis having the chassis management core 106.

[0031] FIG. 4 illustrates a flow diagram of an example method 400 for performing a protocol conversion. In one example, the blocks of the method 400 may be performed by the chassis management abstraction layer 104.

[0032] At block 402, the method 400 begins. At block 404, the method 400 receives, at a chassis, a data packet from a server. For example, the server may be attempting to send a data packet through the chassis to a destination.

[0033] At block 406, the method 400 determines a protocol used by the server to send the data packet. For example, a back-end protocol detector in the chassis may examine the data packet to determine the protocol used by the server. In one example, the back-end protocol detector may scan a header file of the data packet to identify the protocol that is used.

[0034] At block 408, the method 400 determines that a mismatch occurs between the protocol used by the server and a protocol used by the chassis. For example, the server may be using an older protocol version than the chassis. In one example, the controller of the server may be using an earlier server management controller instead of a newer or current server management controller and the chassis may be running a current generation chassis controller, which may be the current chassis protocol version. Thus, the protocol used by the server may mismatch the protocol used by the chassis.

[0035] At block 410, the method 400 enables a conversion of the protocol used by the server to send the data packet to the protocol used by the chassis via a protocol conversion in the chassis. For example, the back-end protocol detector may send a control signal to a mode controller indicating a mismatch. The mode controller may then send a switching command signal to a chassis channel mode switcher to initiate a protocol conversion mode. The chassis channel mode switcher may then divert the data packet to the protocol conversion in the chassis management abstraction layer.

[0036] In one example, the conversion may occur in a layer 1 (e.g., a physical layer), a layer 2 (e.g., a data link layer) or a layer 3 (e.g., a network layer), or any combination thereof, of an Open Systems Interconnect (OSI) model. For example, the conversion may change how the data packet is addressed, formatted, and the like. At block 412, the method 400 ends.

[0037] FIG. 6 illustrates a block diagram of an example non-transitory computer readable storage medium 604 storing instructions 606, 608, 610, and 612 to perform the method 400. The instructions 606, 608, 610, and 612 may be executed by a processor 602 that is in communication with the non-transitory computer readable storage medium 604.

[0038] The instructions 606 may include instructions to receive, at a chassis, a data packet from a server. The instructions 608 may include instructions to determine a protocol used by the server to send the data packet. The instructions 610 may include instructions to determine that a mismatch occurs between the protocol used by the server and a protocol used by the chassis. The instructions 612 may include instructions to enable a conversion of the protocol used by the server to send the data packet to the protocol used by the chassis via a protocol conversion in the chassis.

[0039] FIG. 5 illustrates a flow diagram of an example method 500 for performing a protocol conversion. In one example, the blocks of the method 500 may be performed by the server management abstraction layer 1 16.

[0040] At block 502, the method 500 begins. At block 504, the method 500 receives, at a server, a data packet from a chassis. For example, the chassis may be trying to forward a data packet to a server that is a destination for the data packet.

[0041] At block 506, the method 500 determines a protocol used by the chassis to send the data packet. For example, a front-end protocol detector in the chassis may examine the data packet to determine the protocol used by the chassis. In one example, the front-end protocol detector may scan a header file of the data packet to identify the protocol that is used. [0042] At block 508, the method 500 determines that a mismatch occurs between the protocol used by the chassis and a protocol used by the server. For example, the chassis may be using an older protocol version than the server. In one example, the chassis may be running an earlier generation chassis controller compared to a current generation chassis controller. The controller of the server may be using a current server management controller, which is not compatible with the earlier generation chassis controller. Thus, the protocol used by the chassis may mismatch the protocol used by the server.

[0043] At block 510, the method 500 enables a conversion of the protocol used by the chassis to send the data packet to the protocol used by the server via a protocol conversion in the chassis. For example, the front-end protocol detector may send a control signal to a mode controller indicating a mismatch. The mode controller may then send a switching command signal to a server channel mode switcher to initiate a protocol conversion mode. The server channel mode switcher may then divert the data packet to the protocol conversion in the server management abstraction layer.

[0044] In one example, the conversion may occur in a layer 1 (e.g., a physical layer), a layer 2 (e.g., a data link layer) or a layer 3 (e.g., a network layer), or any combination thereof, of an Open Systems Interconnect (OSI) model. For example, the conversion may change how the data packet is addressed, formatted, and the like. At block 512, the method 500 ends.

[0045] It will be appreciated that variants of the above-disclosed and other features and functions, or alternatives thereof, may be combined into many other different systems or applications. Various presently unforeseen or unanticipated alternatives, modifications, variations, or improvements therein may be subsequently made by those skilled in the art which are also intended to be encompassed by the following claims.

Claims

1 . An apparatus, comprising:

a processor; and

a non-transitory computer-readable storage medium comprising instructions that, when executed by the processor, cause the processor to:

identify a protocol used to send a data packet via a protocol detector;

send a switching command to a mode switcher when a mismatch of the protocol used to send the data packet between a server and a chassis occurs; and

enable a protocol conversion in response to the switching command to convert the data packet into a common protocol between the server and the chassis.

2. The apparatus of claim 1 , wherein the apparatus is coupled to an interface board of the server.

3. The apparatus of claim 2, wherein the apparatus is in communication with a baseboard management controller of the server.

4. The apparatus of claim 1 , wherein the apparatus is coupled to the chassis.

5. The apparatus of claim 1 , wherein the apparatus is configured via at least one of: a general purpose input/output, an interrupt request line, or a serial peripheral interface bus.

6. The apparatus of claim 1 , wherein the mismatch is due to a current protocol associated with the server and an older protocol associated with the chassis.

7. The apparatus of claim 1 , wherein the mismatch is due to a current protocol associated with the chassis and an older protocol associated with the server.

8. A non-transitory computer-readable storage medium encoded with instructions executable by a processor, the computer-readable storage medium comprising:

instructions to receive, at a chassis, a data packet from a server;

instructions to determine a protocol used by the server to send the data packet;

instructions to determine that a mismatch occurs between the protocol used by the server and a protocol used by the chassis; and

instructions to enable a conversion of the protocol used by the server to send the data packet to the protocol used by the chassis via a protocol conversion in the chassis.

9. The non-transitory computer-readable storage medium of claim 8, wherein the instructions to determine the protocol used by the server is determined by a back-end protocol detector.

10. The non-transitory computer-readable storage medium of claim 8, wherein the instructions to enable the conversion is performed by a mode controller that sends a switching command to a chassis channel mode switcher in response to the determining that the mismatch occurs.

1 1 . The non-transitory computer-readable storage medium of claim 8, wherein the conversion occurs in a layer 1 , a layer 2, or a layer 3 of an Open Systems Interconnect (OSI) model.

12. A method, comprising:

receiving, at a server, a data packet from a chassis;

determining a protocol used by the chassis to send the data packet; determining that a mismatch occurs between the protocol used by the chassis and a protocol used by the server; and

enabling a conversion of the protocol used by the chassis to send the data packet to the protocol used by the server via a protocol conversion in the server.

13. The method of claim 12, wherein the determining the protocol used by the chassis is determined by a front end protocol detector.

14. The method of claim 12, wherein the enabling is performed by a mode controller sending a switching command to a server channel mode switcher in response to the determining that the mismatch occurs.

15. The method of claim 12, wherein the conversion occurs in a layer 1 , a layer 2, or a layer 3 of an Open Systems Interconnect (OSI) model.