Cluster system, cluster member, and failure recovery method and program thereof
First Claim
1. A cluster system formed of a plurality of cluster members, wherein each said cluster member,with respect to a packet included in a main processing range indicative of a range of main processing assigned to said cluster member or a sub-processing range indicative of a range of sub-processing among packets applied to said cluster system, executes session processing including processing of recording and updating session information indicative of a state of a session of said packet, andwhen a cluster member in charge of main processing of a packet whose sub-processing is assigned to the cluster member in question develops a failure, takes over the main processing of the packet of said cluster member under failure by using said recorded session information.
1 Assignment
0 Petitions
Accused Products
Abstract
Distribution processing control unit determines a main processing range and a sub-processing range whose charges are taken by a cluster member to which the unit belongs. Among packets multicast to a cluster system, a filter hands over packets matching with the main processing range and the sub-processing range to a session processing unit. The session processing unit conducts session processing (including processing of updating session information stored in a holding unit). Thereafter, when the packet matches with the main processing range, the session processing unit hands the packet over to a packet forwarding unit and when the packet matches with the sub-processing range, abandons the packet. When a cluster member in charge of main processing of a packet whose sub-processing is taken charge of by the cluster member in question develops a failure, a failure recovery unit changes the sub-processing range to the main processing range.
43 Citations
14 Claims
-
1. A cluster system formed of a plurality of cluster members, wherein each said cluster member,
with respect to a packet included in a main processing range indicative of a range of main processing assigned to said cluster member or a sub-processing range indicative of a range of sub-processing among packets applied to said cluster system, executes session processing including processing of recording and updating session information indicative of a state of a session of said packet, and when a cluster member in charge of main processing of a packet whose sub-processing is assigned to the cluster member in question develops a failure, takes over the main processing of the packet of said cluster member under failure by using said recorded session information.
-
3. A cluster system formed of a plurality of cluster members,
each said cluster member comprising: -
a traffic distribution filter which passes, among packets applied to said cluster system, a packet included in a main processing range indicative of a range of main processing assigned to the cluster member in question or a sub-processing range indicative of a range of sub-processing; a session information holding unit in which session information indicative of a state of a session of said packet is stored; a session processing unit which executes, with respect to a packet included in said main processing range or said sub-processing range among packets passing through said traffic distribution filter, session processing including processing of updating session information of said packet stored in said session information holding unit; a packet forwarding unit which conducts processing of forwarding a packet output from the session processing unit; and a failure recovery unit which, when a cluster member in charge of main processing of a packet whose sub-processing is assigned to by the cluster member in question develops a failure, changes said sub-processing range to a main processing range. - View Dependent Claims (4, 5, 6, 7, 8)
-
- 9. A cluster member which, among packets applied to a cluster system having the cluster member in question as a component, a packet included in a main processing range indicative of a range of main processing assigned to said cluster member in question or a sub-processing range indicative of a range of sub-processing, executes session processing including processing of recording and updating session information indicative of a state of a session of said packet, and when a cluster member in charge of main processing of a packet whose sub-processing is assigned to by the cluster member in question develops a failure, takes over the main processing of the packet of said cluster member under failure by using said recorded session information.
-
11. A failure recovery method of a cluster system formed of a plurality of cluster members, wherein each said cluster member,
among packets applied to said cluster system, with respect to a packet included in a main processing range indicative of a range of main processing assigned to said cluster member or a sub-processing range indicative of a range of sub-processing, executes session processing including processing of recording and updating session information indicative of a state of a session of said packet, and when a cluster member in charge of main processing of a packet whose sub-processing is assigned to by the cluster member in question develops a failure, takes over the main processing of the packet of said cluster member under failure by using said recorded session information.
-
13. A computer-readable medium incorporating a program of instructions operable to control a computer to function as a cluster member of a cluster system, the program of instructions comprising:
-
instructions to control said computer, among packets applied to the cluster system, with respect to a packet matching with a main processing range indicative of a range of main processing of which the cluster member in question takes charge or with a sub-processing range indicative of a range of sub-processing, to execute session processing including processing of recording and updating session information indicative of a state of a session to which the packet belongs, and instructions to control said computer, when a cluster member in charge of main processing of a packet whose sub-processing is taken charge of by the cluster member in question develops a failure, to take over the main processing of the packet of which said cluster member developing a failure takes charge by using said recorded session information. - View Dependent Claims (14)
-
Specification