Server machine and network processing method

• US 8,661,128 B2
• Filed: 03/18/2008
• Issued: 02/25/2014
• Est. Priority Date: 01/29/2008
• Status: Expired due to Fees

• Current Assignee: Hitachi, Ltd.
• Original Assignee: Hitachi, Ltd.
• Inventors: Agetsuma, Masakuni, Nakano, Takahiro
• Primary Examiner(s): DOAN, DUYEN MY
• Application Number:
  US12/050,282
• Publication Number:
  US 20090190590A1
• Time in Patent Office: 2,170 Days
• Field of Search: 709/203, 709/226
• US Class Current: 709/226
• CPC Class Codes: H04L 67/10 in which an application is distributed across nodes in the network software deployment G06F8/60; multiprogramming arrangements G06F9/46
• CPC Class Codes: H04L 67/1001 for accessing one among a plurality of replicated servers
• CPC Class Codes: H04L 67/1014 based on the content of a request
• CPC Class Codes: H04L 69/14 Multichannel or multilink protocols
• CPC Class Codes: H04L 69/40 for recovering from a failure of a protocol instance or entity, e.g. service redundancy protocols, protocol state redundancy or protocol service redirection management of faults, events, alarms or notifications in data switching networks H04L41/06
• CPC Class Codes: Y02D 30/50 in wire-line communication networks, e.g. low power modes or reduced link rate

Abstract

An object of the present invention is to provide a server machine and network processing method capable of running a plurality of same server applications at a time on a single OS in a single sever machine.

A server machine comprises a packet dispatching processor for retrieving a destination application group of a communication packet based on first identification information included in a communication packet received by any of a plurality of ports and first management information; for retrieving a plurality of endpoints based on second identification information included in the communication packet and second management information; and for dispatching the communication packet to a server application corresponding to any of the plurality of the retrieved endpoints and belonging to the retrieved application group.

Claims

1. A server, comprising:

a plurality of network interfaces coupled to a client computer through a network, the network interface receiving and sending IP packets, different IP addresses being assigned to the network interfaces;

a processor being configured to execute;

an operating system, a plurality of first applications running on the operating system when a first port number is assigned, and

a plurality of second applications running on the operating system when a second port number is assigned;

a memory unit storing;

the operating system, the first and second applications, first information for managing correspondence between the IP addresses assigned to the network interfaces and process group identifiers so that one of the process group identifiers is uniquely defined for each of the IP addresses, and

second information for managing a plurality of first sockets with respect to the first port number and a plurality of second sockets with respect to the second port number;

the first and second sockets being capable of receiving IP packets where their source IP addresses are any of the IP addresses;

wherein the processor is configured to;

create a plurality of first processes for establishing the first sockets, assign different ones of the process group identifiers to the first processes, create a plurality of second processes for establishing the second sockets, assign different ones of the process group identifiers to the second processes, and

register correspondence between the first sockets and the assigned process group identifiers and correspondence between the second sockets and the assigned process group identifiers with the second information;

wherein the processor is configured, upon receipt of an IP packet from the client computer requesting service designated by either one of the first port number or the second port number at one of the network interfaces, to;

retrieve the process group identifier corresponding to the network interface from the first information, retrieve one of the first and second sockets from the second information by both the designated port number and the process group identifier retrieved from the first information, and send the IP packet to the retrieved socket.

2. A server according to claim 1, wherein the processor is configured to, upon receipt of a request for validating a network interface, to:

assign an IP address to the network interface,

assign one of the process group identifiers associated with the network interface, and

register the correspondence between the IP address assigned to the network interface and the one of the process group identifier with the first information.

3. A server according to claim 1, wherein the processor is configured to, upon receipt of a request for invalidating a network interface, to:

remove the IP address assigned to the network interface from the network interface, and

delete the correspondence between the IP address assigned to the network interface and the process group identifier from the first information.

6. A method according to claim 2, further comprising:

receiving a request for invalidating a network interface associated with the server;

removing an IP address assigned to the network interface from the network interface; and

deleting the correspondence between the IP address assigned to the network interface and the process group identifier from the first information.

4. A method, comprising:

providing first information for managing correspondence between IP addresses assigned to a server and process group identifiers so that one of the process group identifiers is uniquely defined for each of the IP addresses,

creating a plurality of first processes for establishing a plurality of first sockets with respect to a first port number and a plurality of second processes for establishing a plurality of second sockets with respect to a second port number;

the first port number being assigned to a plurality of first applications running on an operating system, the second port number being assigned to a plurality of second applications running on the operating system, the first and second sockets being capable of receiving IP packets where their source IP addresses are any of IP addresses assigned to the server;

assigning different one of the process group identifiers to the first processes, assigning different one of the process group identifiers to the second processes, providing second information for managing the first and second sockets, and registering correspondence between the first sockets and the assigned process group identifiers and correspondence between the second sockets and the assigned process group identifiers with the second information;

receiving an IP packet from a client computer requesting service designated by either one of the first port number or the second port number;

retrieving the process group identifier corresponding to an IP address where the IP packet is received from the first information;

retrieving one of the first and second sockets from the second information by both the designated port number and the process group identifier retrieved from the first information; and

sending the IP packet to the retrieved socket.

5. A method according to claim 4, further comprising:

receiving a request for validating a network interface associated with the server;

assigning an IP address to the network interface;

assigning one of the process group identifiers associated with the network interface; and

registering the correspondence between the IP address assigned to the network interface and the one of the process group identifier with the first information.