公开(公告)号：US20060047858A1

公开(公告)日：2006-03-02

申请号：US10929323

申请日：2004-08-30

申请人： William Atherton ,  Daryl Cromer ,  Richard Dayan ,  Scott Dunham ,  Eric Kern ,  Howard Locker ,  William Schwartz ,  Adam Soderlund

发明人： William Atherton ,  Daryl Cromer ,  Richard Dayan ,  Scott Dunham ,  Eric Kern ,  Howard Locker ,  William Schwartz ,  Adam Soderlund

IPC分类号： G06F3/00

CPC分类号： G06F9/4411

摘要： A method and system for booting up multiple PCI peripheral devices, such that the number of bootable PCI peripheral devices is not limited by the amount of computer system memory that is dedicated to storing executable boot code for the peripheral devices. The executable boot code is stored on a Read Only Memory (ROM) on each peripheral device. When a new PCI peripheral device begins to boot up, a check for available memory space in a ROM scan memory address space is performed. If there is not enough available room in the ROM scan memory address space for the new device's executable boot code, then a ROM scan detection logic pages an image of another peripheral device's executable boot code out of the ROM scan memory address space before storing the new device's executable boot code into the ROM scan memory address space.

摘要翻译： 一种用于引导多个PCI外围设备的方法和系统，使得可引导PCI外围设备的数量不受专用于存储外围设备的可执行引导代码的计算机系统存储器的数量的限制。 可执行启动代码存储在每个外围设备上的只读存储器（ROM）上。 当新的PCI外围设备开始启动时，执行ROM扫描存储器地址空间中可用存储器空间的检查。 如果新设备的可执行启动代码的ROM扫描存储器地址空间中没有足够的可用空间，则ROM扫描检测逻辑在存储新的设备的ROM扫描存储器地址空间之前将另一外围设备的可执行引导代码的映像从ROM扫描存储器地址空间中读出 设备的可执行引导代码进入ROM扫描存储器地址空间。

公开(公告)号：US20070150713A1

公开(公告)日：2007-06-28

申请号：US11316180

申请日：2005-12-22

申请人： Jason Almeida ,  Scott Dunham ,  Eric Kern ,  William Schwartz ,  Adam Soderlund

发明人： Jason Almeida ,  Scott Dunham ,  Eric Kern ,  William Schwartz ,  Adam Soderlund

IPC分类号： G06F9/00

CPC分类号： G06F9/30101 ,  G06F9/4416 ,  G06F9/5061

摘要： Methods and arrangements to dynamically modify the number of processors active in a multi-node data processing system. are contemplated. Embodiments include transformations, code, state machines or other logic to change the portion of BIOS that a processor loads on power-on. In some embodiments, a signal sent over a GPIO pin may flip an address line to the portion of the BIO that a processor loads on power-on. In some embodiments, a service processor may set a GPIO or non-volatile RAM value. The portion of BIOS controlling the powering-up of the processor may read the value and branch depending upon the value. Embodiments also include transformations, code, state machines or other logic to determine the state of a dynamically activated processor. In some embodiments, a processor may read from a local scratch register to determine if it has been dynamically activated. If so, embodiments may then clear the scratch register and put the processor to sleep. Embodiments may then update the tables which describe the resources available to the processor.

摘要翻译： 动态修改在多节点数据处理系统中活动的处理器数量的方法和装置。 被考虑。 实施例包括转换，代码，状态机或其他逻辑，以改变处理器在加电时加载的部分BIOS。 在一些实施例中，通过GPIO引脚发送的信号可以将地址线翻转到处理器在上电时加载的BIO部分。 在一些实施例中，服务处理器可以设置GPIO或非易失性RAM值。 控制处理器加电的BIOS部分可以读取该值并根据该值进行分支。 实施例还包括转换，代码，状态机或其他逻辑以确定动态激活的处理器的状态。 在一些实施例中，处理器可以从本地临时寄存器读取以确定其是否已被动态地激活。 如果是这样，则实施例可以清除划痕寄存器并将处理器置于睡眠状态。 然后，实施例可以更新描述处理器可用资源的表。

公开(公告)号：US20070260672A1

公开(公告)日：2007-11-08

申请号：US11382138

申请日：2006-05-08

申请人： Jason Almeida ,  Scott Dunham ,  Eric Kern ,  William Schwartz ,  Adam Soderlund

发明人： Jason Almeida ,  Scott Dunham ,  Eric Kern ,  William Schwartz ,  Adam Soderlund

IPC分类号： G06F15/16 ,  G06F15/177

CPC分类号： H04L41/0896 ,  G06F11/2284

摘要： Basic server resources may be extended by the completion of a Capacity on Demand (CoD) Agreement. The CoD Agreement provides authorization to the server for activation of inactive resources. A Power On Self Test (POST) works in conjunction with a system management interrupt, a memory unit, and a plurality of Peripheral Component Interconnect (PCI) host bridges to provide for on demand additions of input and output adapters. The adapters may be added during various phases of operation and may be hot pluggable.

摘要翻译： 基本服务器资源可以通过完成“按需扩容（CoD）协议”来扩展。 CoD协议向服务器提供激活非活动资源的授权。 开机自检（POST）与系统管理中断，存储器单元和多个外围组件互连（PCI）主机桥连接起来，以提供输入和输出适配器的按需添加。 可以在操作的各个阶段添加适配器，并且可以是热插拔的。

公开(公告)号：US20050097208A1

公开(公告)日：2005-05-05

申请号：US10698543

申请日：2003-10-31

申请人： Simon Chu ,  Richard Dayan ,  Brandon Ellison ,  Eric Kern ,  William Schwartz ,  Adam Soderlund

发明人： Simon Chu ,  Richard Dayan ,  Brandon Ellison ,  Eric Kern ,  William Schwartz ,  Adam Soderlund

IPC分类号： G06F11/20 ,  G06F15/173 ,  H04L29/14

CPC分类号： G06F11/2043 ,  G06F11/1666 ,  G06F11/2028 ,  G06F11/2035 ,  H04L49/90 ,  H04L69/40

摘要： A method and system for method of removing a node from a multi-node computer. The node receives a system management interrupt (SMI), resulting in a quiescenting of only that node. The SMI receiving node then polls other nodes in the multi-node computer to determine if the SMI affects an operation of any of the other nodes, and quiescents any other node affected by the SMI. Each quiescent node then transfers all of the contents of its system memory to a backup memory in an unaffected remote node in the multi-node computer. The remote node than assumes the function of the removed node that had received the SMI. The method and system thus allows node removal in the event of a hot-swap request or a predicted failure of a node.

公开(公告)号：US20050071587A1

公开(公告)日：2005-03-31

申请号：US10675621

申请日：2003-09-30

申请人： Simon Chu ,  Richard Dayan ,  Brandon Ellison ,  Eric Kern ,  William Schwartz ,  Adam Soderlund

发明人： Simon Chu ,  Richard Dayan ,  Brandon Ellison ,  Eric Kern ,  William Schwartz ,  Adam Soderlund

IPC分类号： G06F12/16

CPC分类号： G06F11/2028 ,  G06F11/203 ,  G06F11/2035 ,  G06F11/2051

摘要： A method and system for method of removing a node from a multi-node computer. The node receives a system management interrupt (SMI), resulting in a quiescenting of only that node. The SMI receiving node then polls other nodes in the multi-node computer to determine if the SMI affects an operation of any of the other nodes, and quiescents any other node affected by the SMI. Each quiescent node then transfers all of the contents of its system memory to a backup memory in an unaffected remote node in the multi-node computer. The remote node than assumes the function of the removed node that had received the SMI. The method and system thus allows node removal in the event of a hot-swap request or a predicted failure of a node.

摘要翻译： 一种从多节点计算机中去除节点的方法和系统。 节点接收到系统管理中断（SMI），导致只有该节点静止。 然后，SMI接收节点轮询多节点计算机中的其他节点，以确定SMI是否影响任何其他节点的操作，并使任何其他节点受SMI影响。 然后，每个静态节点将其系统存储器的所有内容传输到多节点计算机中未受影响的远程节点的备份存储器。 远程节点假定已经接收到SMI的已删除节点的功能。 因此，该方法和系统允许在热交换请求或节点的预测故障的情况下去除节点。

公开(公告)号：US20050071625A1

公开(公告)日：2005-03-31

申请号：US10675623

申请日：2003-09-30

申请人： William Schwartz ,  Adam Soderlund ,  Edward Zorek ,  Jason Almeida ,  Scott Dunham ,  Eric Kern

发明人： William Schwartz ,  Adam Soderlund ,  Edward Zorek ,  Jason Almeida ,  Scott Dunham ,  Eric Kern

IPC分类号： G06F1/24

CPC分类号： G06F15/177 ,  G06F9/4405

摘要： A method, system, and program product supporting dynamic configuring of a multi-node computer. The system includes a scalability management module directly coupled to each node in the multi-node computer. The scalability management module sets and maintains configuration parameters for the multi-node computer, wherein if one of the nodes is removed from the multi-node computer, a hot-spare node can be dynamically configured to replace the removed node without having to reconfiguring or physically reconnect the remaining nodes

摘要翻译： 支持多节点计算机的动态配置的方法，系统和程序产品。 该系统包括直接耦合到多节点计算机中的每个节点的可扩展性管理模块。 所述可扩展性管理模块设置并维护所述多节点计算机的配置参数，其中如果从所述多节点计算机中移除所述节点中的一个节点，则可以动态地配置热备用节点以替换所移除的节点而不必重新配置或 在物理上重新连接剩余的节点

公开(公告)号：US20070124522A1

公开(公告)日：2007-05-31

申请号：US11290071

申请日：2005-11-30

申请人： Brandon Ellison ,  Eric Kern ,  William Schwartz ,  Adam Soderlund

发明人： Brandon Ellison ,  Eric Kern ,  William Schwartz ,  Adam Soderlund

IPC分类号： G06F13/24

CPC分类号： G06F13/24

摘要： In a multi-node system, a node can be dynamically detached (e.g., responsive to an error situation) without impacting the operating system or others of the nodes. Contents of in-use memory at the node to be detached are copied to another node, and a memory map is updated to make the copy transparent to components using the memory. Furthermore, the copied-to memory locations are programmatically blocked to prevent assignment thereof to a memory requester.

摘要翻译： 在多节点系统中，可以动态地分离节点（例如，响应于错误情况）而不影响操作系统或其他节点。 要拆分的节点上的使用中内存的内容将复制到另一个节点，并更新存储器映射以使副本对使用内存的组件透明。 此外，复制到存储器位置被编程地阻止以防止将其分配给存储器请求器。

公开(公告)号：US20060224685A1

公开(公告)日：2006-10-05

申请号：US11092188

申请日：2005-03-29

申请人： Ralph Begun ,  Adam Soderlund

发明人： Ralph Begun ,  Adam Soderlund

IPC分类号： G06F15/16

CPC分类号： G06F15/16

摘要： In a multi-node SMP system, at least one processor per node is enabled to execute the SMM task for the hardware resources that are local to that node. Additionally, each node is allocated its own local SMM code copy in its own SMM memory segment, to allow for improved access and a further reduction in internode traffic. In a preferred embodiment, only a signle processor per node is enabled to execute the SMM tasks, and specific SMM memory locations within the SMM memory segments are allocated and used to report status and results from each node. A root node SMM processor monitors the SMM status entries of the other nodes for completion. To further reduce run-time internode traffic, a per-node resource map is created to identify memory and I/O resources that are specific to a particular node. This per-node resource map is then stored locally within the SMM space on each node, respectively.