Abstract:
본 발명은 경로 장해가 발생한 경우, 장해 경로를 우회하도록 경로의 구성을 재구축하는 정보 통신 시스템에 있어서, 제어부에 가해지는 부하의 경감을 도모하기 위한 것으로, 정보 통신 장치간의 통신을 중계하는 중계 장치는, 자장치와, 자장치의 전단 또는 후단에 배치되어 자장치와 논리적 경로로 접속되는 제1 중계 장치 사이의 제1 통신 상태의 변화를 검출하는 검출부와, 자장치가 중계하는 논리적 경로와는 상이한 다른 논리적 경로를 중계하는 제2 중계 장치로부터, 제2 중계 장치와, 제2 중계 장치의 전단 또는 후단에 배치되어 제2 중계 장치와 논리적 경로로 접속되는 제3 중계 장치 사이의 제2 통신 상태를 취득하는 통신 상태 취득부와, 검출부가 제1 통신 상태의 변화를 검출한 경우, 제1 및 제2 통신 상태의 조합에 따라, 자장치와 제2 중계 장치 사이의 논리적 경로를 유효하게 하는 경로 접속부를 구비한다.
Abstract:
The present invention reconstructs a route composition to detour a defect route and reduces the load of a control unit. A relay device which relaying the communication between information communication devices comprises a child device, a detection unit, a communication state obtainment unit, and a route connection unit. The detection unit detects the change of a first communication state between a first relay device and the detection unit. The communication state obtainment unit obtains a second communication state between a second relay device and a third relay device from the second relay device. The route connection unit is effective to a logical route between the child device and the second relay device according to a combination between the first communication state and the second communication state when the detection unit detects the change of the first communication state. [Reference numerals] (1) Relay device;(2) Detection unit;(3) Communication state obtainment unit;(4) Route connection unit;(5) Processing part;(6) Information collection request issuing unit;(AA) one embodiment of the relay device
Abstract:
본 발명은 복수의 기억 장치를 제어하는 복수의 제어 모듈을 갖는 기억 시스템에 관한 것으로, 제어 모듈의 수가 증가하더라도 저레이턴시의 응답을 유지하면서 실장 구성을 용이하게 하는 것을 목적으로 한다. 복수의 기억 장치(2-0∼2-35)를 백 엔드 라우터(5-0∼5-7)로 각 제어 모듈(4-0∼4-7)의 제2 인터페이스(42)에 접속하고, 모든 제어 모듈이 모든 기억 장치에 액세스할 수 있는 용장성(冗長性)을 유지한다. 또한, 제어 모듈과 제1 스위치 유닛을 백 패널(7)에 인터페이스를 구성하는 신호수가 적은 직렬 버스로 접속한다. 이에 따라, 프린트 기판에서의 실장이 가능하게 된다.
Abstract:
A library device is provided to keep entire operation of the library device in case that a part of components forming the library device is failed and specify the components generating the failure. The library device is equipped with dualized library controllers(Lct1,Lct2), dualized drive command paths(P1,P2), and dualized library controller side ports(14,15,24,25) connecting to the drive command path. The drive command path is dualized by including the first and second drive command path. The library controller side port is dualized by including the first and second port installed to each library controller. The first and second port is respectively connected to the first and second drive command pat. A failed component determiner determines the failed component among the library controllers, the drive command paths, and the ports.
Abstract:
스토리지 가상화 장치와 물리 스토리지 장치와의 사이의 패스의 장해에 대한 내장해성이 높은 컴퓨터 시스템, 및 그에 이용되는 스토리지 가상화 장치를 제공한다. 단수 또는 복수의 호스트 컴퓨터 H1, H2와 접속되는 제1 접속 수단(10)과, 복수의 물리 스토리지 장치 S1, S2와 각각 복수의 패스(2a, 2b), (4a, 4b)로 접속 가능한 제2 접속 수단(12)과, 복수의 물리 스토리지 장치 S1, S2의 기억 영역의 일부 또는 전부를 조합한 기억 영역을, 가상적인 스토리지 장치(22a)로서 상기 호스트 컴퓨터 H1, H2에 인식시키는 스토리지 가상화 수단(22)과, 복수의 패스(2a, 2b), (4a, 4b) 중 어느 하나에 장해가 발생했을 때, 그 패스를 폐색하여, 그 패스가 접속되어 있는 물리 스토리지 장치와 다른 패스에 의해 통신하도록 제어하는 패스 폐색 수단(24b)을 구비한다. 스토리지, 가상화, 장해, 호스트 컴퓨터, 기억 영역, 패스, 폐색
Abstract:
A fault tolerant storage controller utilizing tightly coupled dual controller modules. The controller modules each check to see if another controller module or cache module is present and, if so, then all configuration information with respect to the controller modules and attached devices are shared between them. Configuration information may be entered into either or both of the controller modules and the information is shared dynamically. Each cache module may be "locked" by an individual controller module to prevent the other controller module from inadvertently disturbing the contents of the other controller module's cache. During initialization, each controller module checks for the existence of an associated cache module and, if present, it is immediately "locked" by the controller module. Should a controller module fail or give an indication of a malfunction, the other controller module will disable or "kill" the malfunctioning controller module thereby resetting it and releasing any lock it may have had on its cache module. In those instances where the cache module is a write cache, the surviving controller module can resume operations where the malfunctioning controller module left off and complete any remaining writes to the disabled controller module's storage devices preventing the loss of any host computer data. The controller modules are tolerant of the other controller module failing and then rebooting and the sequence of events is detected and recognized by the surviving controller module such that it does not disable the one that failed. The dual controller modules communicate asynchronously to verify that they are each operational and to exchange and verify configuration information and to provide operational status dynamically.
Abstract:
Scalable data storage techniques are described. In one or more implementations, data is obtained by one or more computing devices that describes fault domains in a storage hierarchy and available storage resources in a data storage pool. Operational characteristics are ascertained, by the one or more computing devices, of devices associated with the available storage resources within one or more levels of the storage hierarchy. Distribution of metadata is assigned by the one or more computing devices to one or more particular data storage devices within the data storage pool based on the described fault domains and the ascertained operational characteristics of devices within one or more levels of the storage hierarchy.
Abstract:
Example embodiments relate to a mesh topology storage cluster with an array based manager. The mesh topology storage may include a first pair of controller nodes to access a first storage volume, and a second pair of controller nodes to access a second storage volume. The mesh topology storage may include an array based manager (ABM) associated with the first pair of controller nodes to monitor paths to the first storage volume via the first pair of controller nodes and to monitor paths to the second storage volume via the second pair of controller nodes. The mesh topology storage may include a passive component associated with the second pair of controller nodes to route ABM-type communications of the second pair of controller nodes to the ABM.
Abstract:
A high performance computing (HPC) system includes computing blades having a first region that includes processors for performing a computation, and a second region that includes non-volatile memory for use in performing the computation and another computing processor for performing data movement and storage. Because data movement and storage are offloaded to the secondary processor, the processors for performing the computation are not interrupted to perform these tasks. A method for use in the HPC system receives instructions in the computing processors and first data in the memory. The method includes receiving second data into the memory while continuing to execute the instructions in the computing processors, without interruption. A computer program product implementing the method is also disclosed.