Unified system area network and switch

• US 9,152,597 B2
• Filed: 04/11/2013
• Issued: 10/06/2015
• Est. Priority Date: 11/05/2009
• Status: Active Grant

• Current Assignee: GigaIO Networks, Inc.
• Original Assignee: RJ Intellectual Property LLC
• Inventors: Maitra, Jayanta Kumar
• Primary Examiner(s): Golabbakhsh, Ebrahim
• Application Number:
  US13/860,976
• Publication Number:
  US 20130227093A1
• Time in Patent Office: 908 Days
• US Class Current: 1/1
• CPC Class Codes: G06F 13/4022 using switching circuits, e.g. switching matrix, connection or expansion network G06F13/4009 takes precedence
• CPC Class Codes: G06F 13/4027 using bus bridges G06F13/4022 takes precedence
• CPC Class Codes: G06F 13/4221 being an input/output bus, e.g. ISA bus, EISA bus, PCI bus, SCSI bus
• CPC Class Codes: H04L 41/0806 for initial configuration or provisioning, e.g. plug-and-play
• CPC Class Codes: H04L 49/35 Switches specially adapted for specific applications

Abstract

A network switch, based on the PCI Express protocol, is disclosed. The switch includes a processor, local memory and a plurality of non-transparent bridges. By configuring the non-transparent bridges appropriately, the network switch can facilitate a number of different communication mechanisms, including TCP/IP communication between servers, server clusters, and virtualized I/O device utilization. For example, the network switch may configure the non-transparent bridges so as to have access to the physical memory of every server attached to it. It can then move data from the memory of any server to the memory of any other server. In another embodiment, the network switch is connected to an I/O device, and multiple servers are given access to that I/O device via virtualized connections.

Claims

1. A method of sharing an I/O device among a plurality of computers, comprising:

connecting each of said plurality of computers to a network switch using PCI Express, said network switch comprising a processing unit and a plurality of non-transparent bridges, one of said non-transparent bridges used to connect to a respective one of said plurality of servers and at least one PCI Express port;

connecting said I/O device to said network switch via said PCI Express port;

using said processing unit in said network switch to enumerate said I/O device and assign an I/O space to said I/O device;

configuring each of said non-transparent bridges, using said processing unit, to utilize said assigned I/O space, such that each of said computers can access said I/O device directly through said network switch.

4. The method of claim 1, wherein said computers request exclusive access to said I/O device from said network switch before accessing said I/O device.

5. The method of claim 4, wherein each of said non-transparent bridges comprises a messaging register and said computers request exclusive access to said I/O device from said network switch via said messaging register.

6. The method of claim 4, wherein said plurality of computers and said network switch are attached to a network connection, and wherein said computers request exclusive access to said I/O device from said network switch via said network connection.

2. A system for sharing a I/O device among two computers, comprising:

a first computer having a first local memory, a first processor and a first PCI Express port,

a second computer having a second local memory, a second processor and a second PCI Express port;

a network switch comprising a third processor, a third local memory, a first non-transparent bridge connected to said first PCI Express port, a second non-transparent bridge connected to said second PCI Express port, and a third bridge connected to said I/O device, wherein said third local memory further comprises computer executable instructions, which when executed by the third processor, allows said third processor to;

enumerate said I/O device and assign an I/O space to said I/O device; and

configure each of said non-transparent bridges to utilize said assigned I/O space, such that each of said computers can access said I/O device directly.

3. The system of claim 2, wherein each of said non-transparent bridges comprises a messaging register, and said third local memory comprises computer executable instructions, which when executed by the third processor, allows said third processor to:

accept access requests to said I/O device from said computers via said messaging register; and

grant exclusive access to one of said computers.