An architecture and methodology for designing, deploying, and managing a distributed application onto a distributed computing system is described.

Architecture for distributed computing system and automated design, deployment, and management of distributed applications

A content delivery and global traffic management network system provides a plurality of caching servers connected to a network. The caching servers host customer content that can be cached and stored, and respond to requests for Web content from clients. If the requested content does not exist in memory or on disk, it generates a request to an origin site to obtain the content. A DNS Server (SPD) load balances network requests among customer Web servers and directs client requests for hosted customer content to the appropriate caching server which is selected by choosing the caching server that is closest to the user, is available, and is the least loaded. SPD also supports persistence and returns the same IP addresses, for a given client. The entire Internet address space is broken up into multiple zones. Each zone is assigned to a group of SPD servers. If an SPD server gets a request from a client that is not in the zone assigned to that SPD server, it forwards the request to the SPD server assigned to that zone. Servers write information about the content delivered to log files that are picked up by a log server.

Content delivery and global traffic management network system

A distributed DNS network includes a central origin server that actually controls the zone, and edge DNS cache servers configured to cache the DNS content of the origin server. The edge DNS cache servers are published as the authoritative servers for customer domains instead of the origin server. When a request for a DNS record results in a cache miss, the edge DNS cache servers get the information from the origin server and cache it for use in response to future requests. Multiple edge DNS cache servers can be deployed at multiple locations. Since an unlimited number of edge DNS cache servers can be deployed, the system is highly scalable. The disclosed techniques protect against DoS attacks, as DNS requests are not made to the origin server directly.

Domain name resolution using a distributed DNS network

A method for determining metrics of a content delivery and global traffic management network provides service metric probes that determine the service availability and metric measurements of types of services provided by a content delivery machine. Latency probes are also provided for determining the latency of various servers within a network. Service metric probes consult a configuration file containing each DNS name in its area and the set of services. Each server in the network has a metric test associated with each service supported by the server which the service metric probes periodically performs metric tests on and records the metric test results which are periodically sent to all of the DNS servers in the network. DNS servers use the test result updates to determine the best server to return for a given DNS name. The latency probe calculates the latency from its location to a client's location using the round trip time for sending a packet to the client to obtain the latency value for that client. The latency probe updates the DNS servers with the clients' latency data. The DNS server uses the latency test data updates to determine the closest server to a client.

Method for determining metrics of a content delivery and global traffic management network

A global server load balancing (GSLB) switch serves as a proxy to an authoritative DNS communicates with numerous site switches which are coupled to host servers serving specific applications. The GSLB switch receives from site switches operational information regarding host servers within the site switches neighborhood. When a client program requests a resolution of a host name, the GSLB switch, acting as a proxy of an authoritative DNS, returns one or more ordered IP addresses for the host name. The IP addresses are ordered using metrics that include the information collected from the site switches. In one instance, the GSLB switch places the address that is deemed “best” at the top of the list.

Global server load balancing

In a system including a collection of cooperating cache servers, such as proxy cache servers, a request can be forwarded to a cooperating cache server if the requested object cannot be found locally. An overload condition is detected if for example, due to reference skew, some objects are in high demand by all the clients and the cache servers that contain those hot objects become overloaded due to forwarded requests. In response, the load is balanced by shifting some or all of the forwarded requests from an overloaded cache server to a less loaded one. Both centralized and distributed load balancing environments are described.

Load balancing cooperating cache servers by shifting forwarded request

Load balancing cooperating cache servers

Dans un systeme comprenant un ensemble de serveurs antememoires cooperatifs, tels que des serveurs antememoires de procuration, une demande peut etre acheminee vers un serveur antememoire cooperatif si l'objet demande ne peut pas etre trouve localement. Un etat de saturation est detecte si, par exemple, du fait d'une obliquite de reference, quelques objets font l'objet d'une demande elevee de tous les clients et si les serveurs antememoires contenant ces objets 'chauds' deviennent satures en raison des demandes transmises. En reponse, la charge est equilibree par transfert de tout ou partie des demandes transmises, du serveur antememoire sature vers un serveur moins charge. L'invention concerne en outre des environnements d'equilibrage des charges tant centralises que distribues.

Kevin Michael Jordan

Papers

Load balancing cooperating cache servers by shifting forwarded request

Load balancing cooperating cache servers

Serveurs antememoires cooperatifs d'equilibrage des charges