FAST MOUNT CACHE
    41.
    发明申请
    FAST MOUNT CACHE 审中-公开
    快速安装缓存

    公开(公告)号:US20140281211A1

    公开(公告)日:2014-09-18

    申请号:US13836073

    申请日:2013-03-15

    IPC分类号: G06F3/06

    摘要: A fast mount cache is provided by any offline storage media for fast volume mount access. The fast mount cache may be used as the first level in a hierarchical storage configuration after the high performance tier for data having high access rates shortly after creation but decreases sharply as the data ages. The fast mount cache stores migrated data from online hard disk drive storage and maintains the data on a volume basis as opposed to a file basis. As the fast mount cache capacity fills, or other events occur triggering a volume change, the fast mount cache erases the volume having the oldest data. While data is maintained on the fast mount cache for periods of time soon after it is migrated, the data may be accessed quickly. After the initial period of time has expired, the data only exists on tape storage or low tier data.

    摘要翻译: 任何脱机存储介质都提供快速安装缓存,以实现快速卷安装访问。 快速安装缓存可以用作分层存储配置中的第一级,在高性能层之后,数据在创建后不久具有高访问速率,但随着数据的老化而急剧下降。 快速安装缓存存储从在线硬盘驱动器存储的迁移数据,并以数据为基础维护数据,而不是基于文件。 随着快速安装缓存容量的填满,或其他事件触发卷更改,快速安装缓存会擦除具有最早数据的卷。 虽然数据在迁移后很快就会在快速安装缓存上维护一段时间,但数据可能会被快速访问。 在初始时间段到期后,数据仅存在于磁带存储或低层数据上。

    Synchronizing Scheduler Interrupts Across Multiple Computing Nodes
    42.
    发明申请
    Synchronizing Scheduler Interrupts Across Multiple Computing Nodes 审中-公开
    跨多个计算节点同步调度程序中断

    公开(公告)号:US20140281036A1

    公开(公告)日:2014-09-18

    申请号:US13828896

    申请日:2013-03-14

    IPC分类号: H04L29/08

    摘要: A method, system and program code for synchronizing scheduler interrupts across multiple nodes of a cluster. Network timers and local scheduling timers are clocked off a system source clock. A processor in each computing node repeatedly reads a network time of day counter. The start of scheduler interrupts is synchronized when the time of day counter is at an integer multiple of a synchronizing integer number of network timer ticks. The processor sends an interprocessor scheduler interrupt to other processors in the node to synchronize scheduling timers in the computing node and throughout the cluster.

    摘要翻译: 用于在群集的多个节点上同步调度程序中断的方法,系统和程序代码。 网络定时器和本地调度定时器从系统源时钟计时。 每个计算节点中的一个处理器重复读取一天的网络时间计数器。 当日间计数器的时间是同步整数个网络计时器滴答的整数倍时,调度程序中断的开始是同步的。 处理器向节点中的其他处理器发送处理器间调度器中断,以同步计算节点和整个集群中的调度计时器。

    Dynamic Assembly and Dispatch of Controlling Software
    43.
    发明申请
    Dynamic Assembly and Dispatch of Controlling Software 审中-公开
    动态组装和调度控制软件

    公开(公告)号:US20140280957A1

    公开(公告)日:2014-09-18

    申请号:US13831671

    申请日:2013-03-15

    IPC分类号: H04L12/911

    摘要: Embodiments of the invention include software that provides an operator or a system service the ability to access, control, or configure a plurality of different data center resources using common sets of functions or commands even though those data center resources natively require different commands to access, control, or configure them. The invention is configured to accept common commands and then translate them from a common command format into device specific commands or command sets. The invention simplifies how data center equipment is controlled and configured.

    摘要翻译: 本发明的实施例包括为操作者或系统服务提供访问,控制或配置多个不同数据中心资源的功能的软件,即使这些数据中心资源本身需要不同的访问命令, 控制或配置它们。 本发明被配置为接受公共命令,然后将它们从公共命令格式转换成特定于设备的命令或命令集。 本发明简化了数据中心设备的控制和配置。

    HIERARCHICAL SYSTEM MANAGER ROLLBACK
    44.
    发明申请
    HIERARCHICAL SYSTEM MANAGER ROLLBACK 有权
    分层系统管理员ROLLBACK

    公开(公告)号:US20140279919A1

    公开(公告)日:2014-09-18

    申请号:US13831771

    申请日:2013-03-15

    IPC分类号: G06F11/14

    摘要: Data state rollover is performed based on data state snapshots and deltas. A series of snapshots is taken of the current data state, an original data state, and data states in between. Deltas are then generated between two sequential snapshots. This results in numerous deltas which represent the difference between consecutive snapshots. Once the deltas are acquired, the deltas may be stored along with the snapshot of the present data state. As such, previous data states may be rolled back to by determining the number of deltas to apply to the current data state to achieve the desired previous data state. In cases where the rollback or rollover fails, deltas may be played against the current data state to a point where the last known trusted and working data point existed.

    摘要翻译: 基于数据状态快照和三角形执行数据状态翻转。 拍摄当前数据状态,原始数据状态以及之间的数据状态的一系列快照。 然后在两个顺序快照之间生成Deltas。 这导致许多三角形表示连续快照之间的区别。 一旦获得了三角洲,三角形可以与当前数据状态的快照一起存储。 这样,先前的数据状态可以通过确定应用于当前数据状态以达到期望的先前数据状态的增量的数量来回滚。 在回滚或翻转失败的情况下,可能会对当前数据状态进行三角波,直到最后一个已知的可信和工作数据点存在。

    Reconfigurable Protocol Tables Within An ASIC
    45.
    发明申请
    Reconfigurable Protocol Tables Within An ASIC 有权
    一个ASIC内的可重构协议表

    公开(公告)号:US20140258679A1

    公开(公告)日:2014-09-11

    申请号:US13788281

    申请日:2013-03-07

    IPC分类号: G06F15/78

    摘要: A high performance computing system is provided with an ASIC that communicates with another device in the system according to a protocol defined by the other device. The ASIC is coupled to a reconfigurable protocol table, in the form of a high speed content-addressable memory (“CAM”). The CAM includes instructions to control the execution of the protocol by the ASIC. The CAM may include instructions to control the ASIC in the event that unanticipated signals or other errors are encountered while executing the protocol. Internal ASIC state data may be routed to the CAM to permit the ASIC to generate a reasonable response to errors either in the design or fabrication of the ASIC or the device with which it is communicating.

    摘要翻译: 高性能计算系统提供有ASIC,其根据由另一设备定义的协议与系统中的另一设备进行通信。 ASIC以高速内容可寻址存储器(“CAM”)的形式耦合到可重配置协议表。 CAM包括用于控制由ASIC执行协议的指令。 CAM可以包括在执行协议时遇到意外的信号或其他错误的情况下控制ASIC的指令。 内部ASIC状态数据可以路由到CAM,以允许ASIC在ASIC或其正在通信的设备的设计或制造中产生对错误的合理响应。

    System and Method for Error Logging
    46.
    发明申请
    System and Method for Error Logging 有权
    错误记录的系统和方法

    公开(公告)号:US20140245079A1

    公开(公告)日:2014-08-28

    申请号:US13780248

    申请日:2013-02-28

    IPC分类号: G06F11/07

    摘要: Error data is read from error registers and written into a buffer. A computing node uses a BIOS to read the error data, rearm the error register and write the data into a memory mapped buffer. A hub chip supports creation of a shared memory system of computing nodes. A management controller in the computing node extracts error data from the buffer. The error data preferably consists essentially of the error register identifiers and the contents of the error registers. A system management node receives the error data from the management controllers in the computing nodes. The system management node may be coupled to but separate from the computing nodes.

    摘要翻译: 错误数据从错误寄存器中读取并写入缓冲区。 计算节点使用BIOS读取错误数据,重新设置错误寄存器并将数据写入存储器映射缓冲区。 集线器芯片支持创建计算节点的共享存储器系统。 计算节点中的管理控制器从缓冲器中提取错误数据。 错误数据优选地基本上由错误寄存器标识符和错误寄存器的内容组成。 系统管理节点从计算节点中的管理控制器接收错误数据。 系统管理节点可以耦合到但是与计算节点分离。

    DYNAMIC RESOURCE SCHEDULING
    48.
    发明申请
    DYNAMIC RESOURCE SCHEDULING 有权
    动态资源调度

    公开(公告)号:US20140068627A1

    公开(公告)日:2014-03-06

    申请号:US13931819

    申请日:2013-06-29

    IPC分类号: G06F9/50

    摘要: Embodiments of the invention relate to a system and method for dynamically scheduling resources using policies to self-optimize resource workloads in a data center. The object of the invention is to allocate resources in the data center dynamically corresponding to a set of policies that are configured by an administrator. Operational parametrics that correlate to the cost of ownership of the data center are monitored and compared to the set of policies configured by the administrator. When the operational parametrics approach or exceed levels that correspond to the set of policies, workloads in the data center are adjusted with the goal of minimizing the cost of ownership of the data center. Such parametrics include yet are not limited to those that relate to resiliency, power balancing, power consumption, power management, error rate, maintenance, and performance.

    摘要翻译: 本发明的实施例涉及使用策略自动调度资源以自我优化数据中心中的资源工作负载的系统和方法。 本发明的目的是动态地分配数据中心中的资源,与由管理员配置的一组策略相对应。 与数据中心所有权成本相关的操作参数被监控,并与管理员配置的一组策略进行比较。 当操作参数方法或超过对应于一组策略的级别时,调整数据中心的工作负载,以最小化数据中心的所有权成本。 这样的参数包括但不限于与弹性,功率平衡,功耗,功率管理,错误率,维护和性能相关的参数。

    System and method for removing data from processor caches in a distributed multi-processor computer system
    49.
    发明授权
    System and method for removing data from processor caches in a distributed multi-processor computer system 有权
    用于从分布式多处理器计算机系统中的处理器高速缓存中移除数据的系统和方法

    公开(公告)号:US08635410B1

    公开(公告)日:2014-01-21

    申请号:US09909700

    申请日:2001-07-20

    申请人: Jeffrey S. Kuskin

    发明人: Jeffrey S. Kuskin

    IPC分类号: G06F12/00

    摘要: A processor interface (24) receives a flush request from a processor (700) and performs a snoop operation to determine whether the data is maintained in a one of the local processors (700) and whether the data has been modified. If the data is maintained locally and it has been modified, an identified local processor (700) receives the flush request from the processor interface (24) and initiates a writeback to a memory directory interface unit (24). If the data is not maintained locally or has not been modified, the processor interface (24) forwards the flush request to the memory directory interface unit (22). Memory directory interface unit (22) determines which remote processors within the system (10) have a copy of the data and forwards the flush request only to those identified processors.

    摘要翻译: 处理器接口(24)从处理器(700)接收刷新请求,并执行窥探操作以确定数据是否被维护在本地处理器(700)中的一个以及数据是否被修改。 如果数据在本地维护并且已被修改,则识别的本地处理器(700)从处理器接口(24)接收刷新请求,并向存储器目录接口单元(24)发起回写。 如果数据未在本地维护或未被修改,则处理器接口(24)将刷新请求转发到存储器目录接口单元(22)。 存储器目录接口单元(22)确定系统(10)内的哪些远程处理器具有数据的副本,并将刷新请求仅转发到那些已识别的处理器。

    Network filesystem asynchronous I/O scheduling
    50.
    发明授权
    Network filesystem asynchronous I/O scheduling 有权
    网络文件系统异步I / O调度

    公开(公告)号:US08635256B2

    公开(公告)日:2014-01-21

    申请号:US10620797

    申请日:2003-07-17

    IPC分类号: G06F17/30

    CPC分类号: G06F21/6218 G06F17/30067

    摘要: Resource acquisition requests for a filesystem are executed under user configurable metering. Initially, a system administrator sets a ratio of N:M for executing N read requests for M write requests. As resource acquisition requests are received by a filesystem server, the resource acquisition requests are sorted into queues, e.g., where read and write requests have at least one queue for each type, plus a separate queue for metadata requests as they are executed ahead of any waiting read or write request. The filesystem server controls execution of the filesystem resource acquisition requests to maintain the ratio set by the system administrator.

    摘要翻译: 文件系统的资源获取请求在用户可配置的测量下执行。 最初,系统管理员设置用于执行M个写入请求的N个读取请求的N:M的比率。 当资源获取请求被文件系统服务器接收时,资源获取请求被排序成队列,例如,其中读取和写入请求对于每种类型具有至少一个队列,加上元数据请求的独立队列,因为它们在任何 等待读或写请求。 文件系统服务器控制文件系统资源获取请求的执行,以维护系统管理员设置的比例。