Method and apparatus for organizing elements of a server application in a client-server system
First Claim
1. A distributed computing system made of a plurality of servers that contains a processor to process computing treatments and a memory to save graphs, routing means between all the servers, interface server to process requests from a plurality of equipments, wherein the plurality of servers is organized in N layers of servers, each layer containing a group of servers, with servers from the same layer organized in a ring topology, each server of the ring having a communication protocol with the following server inside the ring, each server of the group of machines having a communication protocol with a routing server to assure that:
- each server of a layer communicates with each server of the adjacent lower layer;
each server of a layer comprising;
a memory cache to record and save graphs that are specific to a user or a group of users;
a memory cache to record and save hashed data that summarizes the content of graphs hosted in lower layers;
a memory cache to record and save ephemeral results of user'"'"'s operations and treatments, from lower layers and/or user layer; and
a memory cache to record and save ephemeral data gathered from the lower layers.
1 Assignment
0 Petitions
Accused Products
Abstract
A distributed computing system includes a plurality of servers, each server comprising a processor to process computing treatments and a memory system to record and save graphs. The system also includes means of routing between servers and an interface server to treat requests from a plurality of users'"'"' equipment. Servers are organized in N layers of servers, building together a group of servers. Servers from a same layer present a ring topology, and each server has a communication protocol with the following server in the ring of the group of machines. The system also includes communication means with the routing server.
-
Citations
11 Claims
-
1. A distributed computing system made of a plurality of servers that contains a processor to process computing treatments and a memory to save graphs, routing means between all the servers, interface server to process requests from a plurality of equipments, wherein the plurality of servers is organized in N layers of servers, each layer containing a group of servers, with servers from the same layer organized in a ring topology, each server of the ring having a communication protocol with the following server inside the ring, each server of the group of machines having a communication protocol with a routing server to assure that:
-
each server of a layer communicates with each server of the adjacent lower layer; each server of a layer comprising; a memory cache to record and save graphs that are specific to a user or a group of users; a memory cache to record and save hashed data that summarizes the content of graphs hosted in lower layers; a memory cache to record and save ephemeral results of user'"'"'s operations and treatments, from lower layers and/or user layer; and a memory cache to record and save ephemeral data gathered from the lower layers. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9, 11)
-
-
10. A requesting process in real time of a multilayer graph structured information system comprising a set of a group of server machines, a routing server and at least one database server, the group of server machines hosting data specific to the elements of the multilayer graph, the requesting process comprising:
-
instantiation steps of elements of the general multilayer versioned graph comprising; selecting one of the servers depending on parameters such as CPU charge of each server, type of element, similarities between the filiation of the elements already instantiated in the server and filiation of the element to record in the selected server; propagating the instantiation in the network of group of machines; completion steps of the specific hosted data comprising recursively transferring the data between two adjacent layers of servers in response to a detection of a lack of information in an upper layer; recording transferred data in a memory cache associated with servers of the lower and upper layers; and data synchronization steps between lower and upper layers, preserving the integrity of the data structure when users are producing content.
-
Specification