Dynamic port type detection

Patent metadata

Field	Value
Publication number	US-10484518-B2
Application number	US-201916250166-A
Country	US
Kind code	B2
Filing date	Jan 17, 2019
Priority date	Mar 15, 2013
Publication date	Nov 19, 2019
Grant date	Nov 19, 2019

Abstract

A default mode of operation for a link is set at a server upon initialization. A wait pulse repetition time and number of supported modes of operation are set at the server. A protocol identifier is set to the default mode. A link initialization frame including the protocol identifier is transmitted to a port of a switch. Based on failing to receive a handshake response to acknowledge successful decoding of the protocol identifier from the switch prior to expiration of the wait pulse repetition time: the protocol identifier is changed to a next mode of operation, the wait pulse repetition time is reset, and the link initialization frame is transmitted to the port of the switch. Changing the protocol identifier, resetting the wait pulse repetition time, and transmitting the link initialization frame are repeated until the handshake response is received or all supported modes of operation are checked.

First claim

What is claimed:

1. A method for dynamic port type detection, comprising:
setting a default mode of operation for a link at a server upon server initialization;
setting a wait pulse repetition time at the server;
setting a number of supported modes of operation at the server;
setting a protocol identifier to the default mode of operation;
transmitting a link initialization frame comprising the protocol identifier to a port of a switch of a network;
based on failing to receive at the server a handshake response to acknowledge successful decoding of the protocol identifier from the switch prior to expiration of the wait pulse repetition time:
changing the protocol identifier to a next mode of operation selected from the supported modes of operation;
resetting the wait pulse repetition time;
transmitting the link initialization frame to the port of the switch; and
repeating the changing of the protocol identifier, the resetting of the wait pulse repetition time, and the transmitting of the link initialization frame until the handshake response is received or all of the number of supported modes of operation are checked.

2. The method of claim 1 , wherein the link initialization frame is defined at one or more of a physical layer and a link layer.

3. The method of claim 2 , further comprising:
resetting one or more of the physical layer and the link layer to configure the port of the switch based on one or more of: receiving a link reset request at the port and sending a link disable signal from the port, wherein the link disable signal is configured to wraparound from an output of the port to a port reset circuit.

4. The method of claim 1 , further comprising:
based on updating a table in the switch, updating port and protocol information in a network controller configured to control the switch, wherein the table comprises a plurality of entries defining a plurality of packet routing paths for a plurality of flows within the network to forward a plurality of packets from at least one port of the switch to one or more other ports of the network based on a header format of the plurality of packets.

5. The method of claim 1 , further comprising:
periodically transmitting the link initialization frame from the server through the link to the switch upon link initialization; and
based on receiving the handshake response at the server, updating configuration information at the server indicating that the port of the switch is set to a mode of operation compatible with the protocol identifier, wherein the mode of operation establishes a highest permitted data rate for the link.

6. The method of claim 1 , further comprising:
based on receiving the handshake response at the server, updating the default mode of operation for the link to correspond with a most recent protocol identifier sent in a most recently acknowledged link initialization frame.

7. The method of claim 1 , wherein the protocol identifier identifies a protocol selected from: Ethernet, Fibre Channel, Fibre Channel over Ethernet (FCoE), internet Wide Area Remote direct memory access Protocol (iWARP), and Remote direct memory access over Converged Ethernet (RoCE).

8. A system for dynamic port type detection, comprising:
a network controller;
a switch coupled to the network controller by a secure channel, the switch comprising a port coupled to a server by a link in a network; and
the server configured to perform a method comprising:
setting a default mode of operation for the link upon server initialization;
setting a wait pulse repetition time;
setting a number of supported modes of operation;
setting a protocol identifier to the default mode of operation;
transmitting a link initialization frame comprising the protocol identifier to the port of the switch of the network;
based on fading to receive a handshake response to acknowledge successful decoding of the protocol identifier from the switch prior to expiration of the wait pulse repetition time:
changing the protocol identifier to a next mode of operation selected from the supported modes of operation;
resetting the wait pulse repetition time;
transmitting the link initialization frame to the port of the switch; and
repeating the changing of the protocol identifier, the resetting of the wait pulse repetition time, and the transmitting of the link initialization frame until the handshake response is received or all of the number of supported modes of operation are checked.

9. The system of claim 8 , wherein the link initialization frame is defined at one or more of a physical layer and a link layer.

10. The system of claim 9 , wherein the switch is configured to reset one or more of the physical layer and the link layer to configure the port of the switch based on one or more of receiving a link reset request at the port and sending a link disable signal from the port, wherein the link disable signal is configured to wraparound from an output of the port to a port reset circuit.

11. The system of claim 8 , further comprising:
based on updating a table in the switch, a plurality of port and protocol information in the network controller is configured to control the switch, wherein the table comprises a plurality of entries defining a plurality of packet routing paths for a plurality of flows within the network to forward a plurality of packets from at least one port of the switch to one or more other ports of the network based on a header format of the plurality of packets.

12. The system of claim 8 , wherein the server is configured to perform the method comprising:
periodically transmitting the link initialization frame from the server through the link to the switch upon link initialization; and
based on receiving the handshake response at the server, updating configuration information at the server indicating that the port of the switch is set to a mode of operation compatible with the protocol identifier, wherein the mode of operation establishes a highest permitted data rate for the link.

13. The system of claim 8 , wherein the server is further configured to perform:
based on receiving the handshake response at the server, updating the default mode of operation for the link to correspond with a most recent protocol identifier sent in a most recently acknowledged link initialization frame.

14. The system of claim 8 , wherein the protocol identifier identifies a protocol selected from: Ethernet, Fibre Channel, Fibre Channel over Ethernet (FCoE), Internet Wide Area Remote direct memory access Protocol (iWARP), and Remote direct memory access over Converged Ethernet (RoCE).

15. A computer program product for dynamic port type detection, the computer program product comprising:
a non-transitory storage medium readable by a processing circuit and storing instructions for execution by the processing circuit for performing a method comprising:
setting a default mode of operation for a link at a server upon server initialization;
setting a wait pulse repetition time at the server;
setting a number of supported modes of operation at the server;
setting a protocol identifier to the default mode of operation;
transmitting a link initialization frame comprising the protocol identifier to a port of a switch of a network;
based on failing to receive at the server a handshake response to acknowledge successful decoding of the protocol identifier from the switch prior to expiration of the wait pulse repetition time:
changing the protocol identifier to a next mode of operation selected from the supported modes of operation;
resetting the wait pulse repetition time;

Assignees

• IBM

Inventors

• Decusatis Casimer
• Krishnamurthy Rajaram B

Classifications

• H04L41/0823

  characterised by the purposes of a change of settings, e.g. optimising configuration for enhancing reliability (for optimising operational conditions of wireless networks H04W24/02) · CPC title

• H04L69/22 Primary

  Parsing or analysis of headers · CPC title

• H04L41/0809

  Plug-and-play configuration · CPC title

• H04L69/18

  Multiprotocol handlers, e.g. single devices capable of handling multiple protocols · CPC title

• H04L41/0866

  Checking the configuration · CPC title