公开(公告)号：JPH1040229A

公开(公告)日：1998-02-13

申请号：JP10068297

申请日：1997-04-17

Applicant: IBM

Inventor： BADOVINATZ PETER RICHARD ,  CHANDRA TUSHAR DEEPAK ,  GOPAL AJEI SARAT ,  KIRBY ORVALLE THEODORE ,  PERSHING JR JOHN ARTHUR

IPC: G06F15/177 ,  G06F9/50 ,  G06F11/20 ,  G06F15/173 ,  G06F15/16

Abstract: PROBLEM TO BE SOLVED: To provide a system for managing the membership of a processor group in distribution computing environment. SOLUTION: Specified action is identified and executed in order to manage the membership of a group. A processor requests subscription to the processor group and is added to the group. In a same way, the processor can request a leaving from the group and can be removed from the group owing to fault occurrence. The group of the members receives a multicast outputted from one member within the group to another member of the group. Moreover, the respective groups of the processors in distribution computing environment has a group leader for controlling action to be executed for the group of the members.

公开(公告)号：JPH1040226A

公开(公告)日：1998-02-13

申请号：JP10066997

申请日：1997-04-17

Applicant: IBM

Inventor： BADOVINATZ PETER RICHARD ,  CHANDRA TUSHAR DEEPAK ,  KIRBY ORVALLE THEODORE ,  PERSHING JR JOHN ARTHUR

IPC: G06F15/177 ,  G06F9/50 ,  G06F11/20 ,  G06F15/16

Abstract: PROBLEM TO BE SOLVED: To provide a method for recovering a group leader in distribution computing environment. SOLUTION: When a fault occurs in the present leader of a processor group which is executed inside distribution computing environment, the new leader is selected. The new group leader is selected from a membership list which follows the subscription order of processorsin the processor group. The selected leader is the succeeding processor after the group leader where the fault occurs in the membership list. Concretely speaking, it is a succeeding active processor in the membership list. After the new group leader is selected, the new group leader is reported to the processor group.

公开(公告)号：JPH1040227A

公开(公告)日：1998-02-13

申请号：JP10067997

申请日：1997-04-17

Applicant: IBM

Inventor： BADOVINATZ PETER RICHARD ,  CHANDRA TUSHAR DEEPAK ,  KIRBY ORVALLE THEODORE ,  PERSHING JR JOHN ARTHUR

IPC: G06F15/177 ,  G06F9/50 ,  G06F11/20 ,  G06F15/16

Abstract: PROBLEM TO BE SOLVED: To provide a method for recovering a group leader in distribution computing environment. SOLUTION: When a fault occurs in the present leader of a processor group which is executed inside distribution computing environment, the new leader is selected. The new group leader is selected from a membership list which follows the subscription order of processors in the processor group. The selected leader is the succeeding processor after the group leader where the fault occurs in the membership list. Concretely speaking, it is a succeeding active processor in the membership list. After the new group leader is selected, the new group leader is reported to the processor group.

公开(公告)号：JPH1040222A

公开(公告)日：1998-02-13

申请号：JP10065297

申请日：1997-04-17

Applicant: IBM

Inventor： BADOVINATZ PETER RICHARD ,  CHANDRA TUSHAR DEEPAK ,  GOPAL AJEI SARAT ,  KIRBY ORVALLE THEODORE ,  PERSHING JR JOHN ARTHUR

IPC: G06F11/20 ,  G06F9/50 ,  G06F15/177 ,  G06F15/16

Abstract: PROBLEM TO BE SOLVED: To provide a method for managing the membership of a processor group in distribution computing environment. SOLUTION: Specified action is identified in order to manage the membership of the group and executed. The processor requests to become a member of the processor group to enter the group. In the same way, the processor can request to be free from the group and can be free from the group owing to fault occurrence. In a member group, a multicast is received which is issued from one of the members of the group to another member of the group. Besides, the respective processor groups in distribution computing environment have group leader for controlling action which is executed for the group of the members.

公开(公告)号：DE3853257D1

公开(公告)日：1995-04-13

申请号：DE3853257

申请日：1988-09-20

Applicant: IBM

Inventor： HALIM NAGUI ,  NIKOLAOU CHRISTOS NICHOLAS ,  PERSHING JR JOHN ARTHUR

IPC: G06F15/16 ,  G06F9/50 ,  G06F15/173 ,  H04L29/00

Abstract: A method and apparatus for coupled computer systems provides a single network node image when connected to a computer network, so that the network is unaware of the "fine" structure of the computer systems in the machine room. The coupled complex is made available to the network.

公开(公告)号：DE3853257T2

公开(公告)日：1995-09-14

申请号：DE3853257

申请日：1988-09-20

Applicant: IBM

Inventor： HALIM NAGUI ,  NIKOLAOU CHRISTOS NICHOLAS ,  PERSHING JR JOHN ARTHUR

IPC: G06F15/16 ,  G06F9/50 ,  G06F15/173 ,  H04L29/00

Abstract: A method and apparatus for coupled computer systems provides a single network node image when connected to a computer network, so that the network is unaware of the "fine" structure of the computer systems in the machine room. The coupled complex is made available to the network.