AUTONOMOUS RESOURCE GOVERNOR IN DISTRIBUTED SYSTEMS FOR PROTECTING SHARED RESOURCES

    公开(公告)号:US20180278542A1

    公开(公告)日:2018-09-27

    申请号:US15468097

    申请日:2017-03-23

    CPC classification number: H04L67/1036

    Abstract: Variety of approaches to provide an autonomous governor in a distributed system for preserving a shared resource are described. A hosted service initiates operations to provide the autonomous governor upon determining the shared resource to be managed. An initial lease count is designated to the shared resource. The initial lease count corresponds to an estimated capacity of the shared resource. Next, an assigned lease count is determined by incrementing or decrementing the initial lease count based on a detected actual capacity of the shared resource. Upon detecting a steady state of the assigned lease count, the assigned lease count is incremented to determine whether the actual capacity of the shared resource is increased.

    LOAD SHARING METHOD, APPARATUS, AND SYSTEM
    106.
    发明申请

    公开(公告)号:US20180234344A1

    公开(公告)日:2018-08-16

    申请号:US15954616

    申请日:2018-04-17

    Abstract: Embodiments of the present application disclose a load sharing method, apparatus, and system. The method includes: obtaining, by a controller, a load parameter of a target network device; determining, by the controller according to the load parameter, whether the target network device is in an overloaded state; and sending, by the controller, first configuration information to the target network device when the target network device is in the overloaded state, where the target network device is configured to be in a first state according to the first configuration information, and the first state instructs the target network device to delay or skip returning a PADO packet when receiving a PADI packet. According to the embodiments of the present application, not only load of network devices in a network is more balanced, but also a difficulty in implementing network load balance is small and costs are low.

    Determining an application delivery server based on geo-location information

    公开(公告)号:US09960967B2

    公开(公告)日:2018-05-01

    申请号:US12603471

    申请日:2009-10-21

    Abstract: A method and system to determine a web server based on geo-location information is disclosed. The system includes: a local DNS server coupled to a web client; a plurality of web servers; and a global load balancer coupled to the local DNS server. The global load balancer: receives a request for a web service sent by the web client, the request comprising local DNS server information; determines a geographic location for the local DNS server based on the local DNS server information; determines a web server from the plurality of web servers based on the requested web service; determines a geographic location for the determined web server; determines that the geographic location for the local DNS server matches the geographic location for the determined web server; selects the determined web server; and sends a response comprising information on the selected web server to the local DNS server.

    STRING SEARCH AND MATCHING FOR GATE FUNCTIONALITY

    公开(公告)号:US20180083921A1

    公开(公告)日:2018-03-22

    申请号:US15825924

    申请日:2017-11-29

    Abstract: Fast string search and matching is critical for many security tasks in particular if these have “gate functionality” for instance as found in access control applications, firewalls, routers, and load balancers. The fast matching of strings is essential to impose and enforce access control policies without creating bottlenecks. Firewalls protect networks by monitoring the traffic crossing the network perimeter. The number of packet matching rules firewalls can effectively handle is limited by the matching time and space complexity of the algorithms employed. A new approach implements matching independent of the number of rules and linear in the length of the rule to be matched. A data structure used in this approach is referred to as a “Bipartite Concatenated Representation” (BCR). The space complexity of the BCR within this application scenario scales as O(N log2 N) where N is the number of rules.

Patent Agency Ranking