Abstract:
A method for providing a virtual machine for a real time virtual desktop service is disclosed. The method for providing a virtual machine for a real time virtual desktop service according to the present invention comprises the following steps: a client part transmits user information to a service gateway; the service gateway searches for access information of a virtual machine corresponding to the user information; the service gateway provides the access information for the client part; the client part accesses a service provider server corresponding to the access information; and the service provider server provides the virtual machine for the client part.
Abstract:
A power redundant device of a rack-mounted server according to the present invention, in which a plurality of servers are detachably loaded, comprises a first server with first and second connectors connected to an output side of a first power supply unit in parallel; a second server with third and fourth connectors connected to an output side of a second power supply unit in parallel; and a power connection cable connecting the first connector with the third connector or the second connector with the fourth connector.
Abstract:
Disclosed in the present invention are a system for controlling the internal temperature of an internet data center and a method thereof. The system for controlling the internal temperature of the internet data center, arranging rear surfaces of server racks to face each other, comprises: a cooling device for discharging the internal air out of the data center or inducing the external air into the data center according to a change of the internal temperature caused by a heated air within the data center by controlling a blower; and a management server for comparing the internal temperature with the set temperature and outputting a control signal to control an air discharge blower and an air supply blower within a cooling device according to the comparison result. [Reference numerals] (100) Cooling device
Abstract:
PURPOSE: A dynamic load distribution system and method thereof are provided to minimize resource wastes by hierarchically managing services and resources in a mass cluster computing system. CONSTITUTION: A resource management master(2000) manages a bear server(2100) which does not execute services. The resource management master includes a hierarchical structure. A service master(1000) dynamically allocates the bear servers to a load distribution server(1100) or a service server(1200) or dynamically releases the allocated load distribution server or the service execution server to the bear server by considering of requirements of the services and monitoring information for the state or performance of the server.
Abstract:
Provided are a large-scale cluster monitoring system and a method for automatically building/restoring the same, which can automatically build a large-scale monitoring system and can automatically build a monitoring environment when a failure occurs in nodes. The large-scale cluster monitoring system includes a CM server, a BD server, GM nodes, NA nodes, and a DB agent. The CM server manages nodes in a large-scale cluster system. The DB server stores monitoring information that is state information of nodes in groups. The GM nodes respectively collect the monitoring information that is the state information of the nodes in the corresponding groups to store the collected monitoring information in the DB server. The NA nodes access the CM server to obtain GM node information and respectively collect the state information of the nodes in the corresponding groups to transfer the collected state information to the corresponding GM nodes. The DB agent monitors the monitoring information of the nodes in the groups, which is stored in the DB server, to detect a possible node failure.
Abstract:
An apparatus and a method for accelerating streaming of a network storage based on a fiber channel for streaming data sharing are provided to access data of a corresponding disk storage device through another FC-NS card, thereby performing streaming and other works. A disk controller(216) controls a FC disk storage connected to an FC-NS(Fiber Channel-Network Storage) card(210). A PMEM(Peripheral component interconnect MEMory) generator searches a PMEM(218) mounted on the FC-NS card. The PMEM generator generates a management structure for managing the PMEM. A PMEM manager assigns the PMEM to a buffer for non-copying streaming.
Abstract:
An IDR(Instantaneous Decoding Refresh) unit producing method and a system and method of trick play by using the same are provided to preserve the transmission rate of original contents and to minimize the load of a server, thereby controlling the speed. A speed information input member(21) receives the speed information. A transmission condition determining member(22) determines the transmission condition of the IDR unit on the basis of the speed information inputted through the speed information input member. An IDR unit producing member(23) controls the number and data amount of the video framed to be transmitted and produces the IDR unit. A transmission member(24) transmits the IDR unit produced by the IDR unit producing member to the external user terminal according to the transmission condition determined by the transmission condition determining member. The transmission condition determining member determines 'transmission' or 'jump' of the IDR unit according to the resulting value of the inputted speed value over 2 minus 1.