Dynamic execution unit management for high performance user...

Details Dynamic execution unit management for high performance user... Dynamic execution unit management for high performance user...

1996-03-08

2001-01-30

Banankhah, Majid (Department: 2755)

Electrical computers and digital processing systems: multicomput

Computer-to-computer data routing

Least weight routing

C709S203000, C709S226000

Reexamination Certificate

active

06182109

ABSTRACT:

BACKGROUND OF THE INVENTION
This invention relates generally to data communication on computer networks and computer protocols which facilitate such communication. More particularly, it relates to an object oriented communication interface for network protocol access.
In the very early days of computing, computer systems were standalone processors to which peripheral devices such as displays and printers and input devices were connected. Each computer system was independent and there was little communication between computer systems. Today, it is well known to interconnect computer systems in computer networks such as local area networks or wide area networks to achieve a variety of benefits including the sharing of data, services and resources available from the various computer systems coupled to the networks.
To communicate between the different computer systems along a network, many communication protocols have been developed. Some examples of well-known network protocols include the System Network Architecture (SNA), Transmission Control Protocol/Internet Protocol (TCP/IP), Network Basic Input Output System (NetBIOS), and Internet Packet Exchange/Sequence Packet Exchange (IPX/SPX). Other communication protocols are known and widely used and described in various standards of ISO, IEEE and other organizations. To facilitate an understanding of the computer network, the network functions and associated software are often described as a series of layers. Data transfer between one copy of a distributed application over the network to another copy of the distributed application is accomplished by using the services of an underlying series of communication layers. Generally, each layer in one computer system has a counterpart layer in the receiving computer system so that each layer communicates with respective peer layers.
The seven layer Open Systems Interconnect (OSI) model is one of the best known descriptions of network communications, although many communication implementations combine or omit one or more of the OSI layers. In OSI, the physical layer is the lowest layer which interacts directly with the network. It includes the actual bit stream transmission across the physical connections to the network. The second layer is the datalink layer which provides multiplexing and framing of the physical layer stream into messages. It also provides error detection, synchronization information and physical channel management. The third layer is the network layer which controls routing of information through the network. Services such as addressing, network initialization, switching, segmenting and formatting are provided in this layer. Sometimes acknowledgement of data delivery is accomplished in this layer; sometimes in the datalink layer.
The fourth layer is the transport layer which controls transparent data delivery, multiplexing and mapping. Reliable delivery as opposed to best effort in the layers below is accomplished by this layer if desired by the application. Services such as retransmission of missing data, reordering of data delivered out of order and correction of transmission errors are usually accomplished in this layer. The fifth layer is the session layer which uses the information from the transport layer to group pieces of data together as a common activity between two nodes in the network called a session. The sixth layer is the presentation layer which includes the interface between the session layer and the seventh layer the application layer. The presentation layer presents the information for use in the application layer without compromising the integrity of the session layer. The presentation layer provides data interpretation and format and code transformation while the application layer provides user application interfaces and management functions.
Another well known network standard is the IEEE Standard. The primary difference between the IEEE model and OSI, is the splitting of the second OSI layer, the datalink layer into two sublayers, the media access layer (MAC) sublayer and the logical link control (LCC) sublayer. Media access control manages the medium access attachment in its control access to the communications media. The logical link control provides state machine for supporting the protocol specified by an associated data link control.
Another well known technology is object oriented programming which encapsulates data and methods into a programming entity called an object. By protecting certain methods and data through a public interface, an object oriented program can insulate each component from changes to other components yet provide the needed functions with a minimum of reprogramming. For more background information on object oriented technologies, concepts and conventions, the reader is referred to references such as
Object Oriented Design With Applications,
Grady Booch (The Benjamin/Cummins Publishing Company, 1990) and
Object Oriented Software Construction,
by B. Meyer, (Prentice Hall, 1988).
There have been previous attempts to apply object oriented technology to the general area of communication protocol in a multiprocessor network. As will be seen below, it remains a fertile area of invention.
SUMMARY OF THE INVENTION
A method, system and product for dynamically managing a pool of execution units in a server system, the pool devoted to a communication process between client and server processes. A minimum and a maximum number of execution units in the communication process poolis established. The minimum number of execution units is the number necessary to support a typical client load. The maximum number of execution units is an upper bound to support a peak client load without overloading the server system. As client requests for service are received by the server system, a number of determinations are made. It is determined whether assigning an execution unit to the request would bring a current number of execution units in the communication process pool over the maximum number of execution units. If so, the client request is rejected. It is determined whether assigning an execution unit to the request would bring the number of assigned execution units to a client task making the request over an allotted number of execution units for the client task. If so, the client request is rejected. If the determinations are negative, thereby assigning an execution unit in the communication process pool is assigned to the client request. The number of unused execution units in the communication pool is periodically reviewed to determine whether it should be increased or decreased to improve system performace.


REFERENCES:
patent: 4099235 (1978-07-01), Hoschler et al.
patent: 4748558 (1988-05-01), Hirosawa et al.
patent: 5021949 (1991-06-01), Morten et al.
patent: 5249290 (1993-09-01), Heizer
patent: 5341477 (1994-08-01), Pitkin et al.
patent: 5446737 (1995-08-01), Cidon et al.
patent: 5504894 (1996-04-01), Ferguson et al.
patent: 5515508 (1996-05-01), Pettus et al.
patent: 5515538 (1996-05-01), Kleiman
patent: 5517643 (1996-05-01), Davy
patent: 5553083 (1996-09-01), Miller
patent: 5603029 (1997-02-01), Aman et al.
patent: 5752030 (1998-05-01), Konno et al.
patent: 5752031 (1998-05-01), Cutler et al.
patent: 5774668 (1998-06-01), Choquier et al.
patent: 5799173 (1998-08-01), Gossler et al.
patent: 0384339A2 (1990-08-01), None
patent: 384339A2 (1990-08-01), None
patent: 413490A2 (1991-02-01), None
patent: 0413490A2 (1991-02-01), None
patent: 0473913A2 (1992-03-01), None
patent: 0666665A2 (1995-01-01), None
patent: 0694837A1 (1996-01-01), None
IBM TDB, “Control of Dynamic Threads Pool for Concurrent Remote Procedure Calls”, vol. 38, No. 5, pp. 199-200, May 1995.
Rodley, John, “Thread Programming in UNIXWARE 2.0” Dr. Dobb's v20 n6 p(56)7, Jun. 1995.
Frentzen et al, “Secure Servers” PC Week, v12 n43 p95(2), Oct. 1995.
Hajek, “Performance of global load balancing by local adjustment”, IEEE digital library, 1990.
Lin et al, “A dynamic load balancing policy with a central job dispatcher”, IEEE digital library, 1991.

Affiliated with

Also associated with

Rating

Dynamic execution unit management for high performance user... does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Dynamic execution unit management for high performance user..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Dynamic execution unit management for high performance user... will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-2450800