Method of indicating processes resident within a cell of a data processing system
First Claim
1. In a distributed data processing system comprising a plurality of individual cells, a method of determining whether a given process is resident within one of said cells, said method comprising the steps of:
- (a) providing in each of said plurality of cells a table of resident processes, said table comprising the names of processes resident within said cell;
(b) sending a discovery message from a first cell to a second cell, said discovery message comprising the name of said given process and the location of said first cell; and
(c) determining whether the table of resident processes for said second cell contains the name of said given process;
(i) if said given process is resident within said second cell, informing said first cell of the location of said second cell; and
(ii) if said process is not resident within said second cell, sending said discovery message to successive different cells in said system, until one cell'"'"'s table of resident processes contains the name of said given process, in which case said first cell is informed of the location of said one cell, or until said discovery message has been received by all other cells in the system without finding the name of said given process in any table of resident processes, in which case said first cell is informed that said given process is not located in any cell of said system.
1 Assignment
0 Petitions
Accused Products
Abstract
A multi-processor, multi-tasking virtual machine comprises processes, messages, and contexts. Processes communicate only through messages. Contexts are groups of related processes. The virtual machine is implemented in a distributed data processing system comprising a plurality of individual cells coupled by a local area network (LAN). Each cell may comprise one or more processes and/or contexts.
A network interface module (NIM) provides the interface between any individual cell and the LAN. To facilitate message transmission between processes resident on different cells, each NIM is provided with tables identifying the locations of resident and non-resident processes, respectively. Cells may be added to or deleted from the LAN without disrupting the LAN operations.
84 Citations
12 Claims
-
1. In a distributed data processing system comprising a plurality of individual cells, a method of determining whether a given process is resident within one of said cells, said method comprising the steps of:
-
(a) providing in each of said plurality of cells a table of resident processes, said table comprising the names of processes resident within said cell; (b) sending a discovery message from a first cell to a second cell, said discovery message comprising the name of said given process and the location of said first cell; and (c) determining whether the table of resident processes for said second cell contains the name of said given process; (i) if said given process is resident within said second cell, informing said first cell of the location of said second cell; and (ii) if said process is not resident within said second cell, sending said discovery message to successive different cells in said system, until one cell'"'"'s table of resident processes contains the name of said given process, in which case said first cell is informed of the location of said one cell, or until said discovery message has been received by all other cells in the system without finding the name of said given process in any table of resident processes, in which case said first cell is informed that said given process is not located in any cell of said system. - View Dependent Claims (2)
-
-
3. In a distributed data processing system comprising a plurality of individual cells, a method of
indicating the process resident within one of said cells, and of notifying the remainder of said plurality of individual cells of changes in the number of processes resident within said one cell, said method comprising the steps of: -
(a) providing in said one cell a table of resident processes, each entry in said table comprising a first portion corresponding to the name of a process which is resident within said one cell; (b) when a process is created in said one cell whose name is not currently contained with said table of resident processes, making a new entry in said table of resident processes corresponding to said newly created process; (c) generating a notification message comprising the name of said newly created process and the location of said one cell; and (d) sending said notification message to a next cell. - View Dependent Claims (4, 5, 6, 7, 8, 9, 10, 11, 12)
-
Specification