MULTI-LAYER AUTOSCALING FOR A SCALE-UP CLOUD SERVER

    公开(公告)号:US20190079845A1

    公开(公告)日:2019-03-14

    申请号:US15698726

    申请日:2017-09-08

    IPC分类号: G06F11/34 G06F9/455 G06F9/50

    摘要: A computer-implemented scaling method, an apparatus, and a computer program product for detecting whether a performance of a system reaches a target performance are provided. The method includes scaling a layered software environment, including scaling a first layer software environment in the layered software environment in response to the performance of the system not reaching the target performance and scaling a second layer software environment that is above the first layer software environment in the layered software environment in response to the performance of the system not reaching the target performance despite the first layer software environment being scaled. The method also includes scaling hardware resources used for executing the layered software environment in the system in response to the performance of the system not reaching the target performance before scaling of the first layer software environment or after scaling of the second layer software environment.

    Parallel Execution Mechanism and Operating Method Thereof
    3.
    发明申请
    Parallel Execution Mechanism and Operating Method Thereof 有权
    并行执行机制及其操作方法

    公开(公告)号:US20140115249A1

    公开(公告)日:2014-04-24

    申请号:US14061775

    申请日:2013-10-24

    IPC分类号: G06F17/30

    摘要: A thread priority control mechanism is provided which uses the completion event of the preceding transaction to raise the priority of the next transaction in the order of execution when the transaction status has been changed from speculative to non-speculative. In one aspect of the present invention, a thread-level speculation mechanism is provided which has content-addressable memory, an address register and a comparator for recording transaction footprints, and a control logic circuit for supporting memory synchronization instructions. This supports hardware transaction memory in detecting transaction conflicts. This thread-level speculation mechanism includes a priority up bit for recording an attribute operand in a memory synchronization instruction, a means for generating a priority up event when a thread wake-up event has occurred and the priority up bit is 1, and a means for preventing the CAM from storing the load/store address when the instruction is a non-transaction instruction.

    摘要翻译: 提供一种线程优先级控制机制,当事务状态从投机状态改变为非投机状态时,使用前一事务的完成事件以执行顺序提高下一事务的优先级。 在本发明的一个方面,提供一种线程级推测机制,其具有内容可寻址存储器,地址寄存器和用于记录事务占用的比较器,以及用于支持存储器同步指令的控制逻辑电路。 这支持硬件事务内存检测事务冲突。 该线程级推测机制包括用于在存储器同步指令中记录属性操作数的优先级上位;当线程唤醒事件发生并且优先级上升位为1时产生优先级上升事件的装置;以及装置 用于在指令是非事务指令时防止CAM存储加载/存储地址。

    Securing pods in a container orchestration environment

    公开(公告)号:US11947660B2

    公开(公告)日:2024-04-02

    申请号:US17446478

    申请日:2021-08-31

    摘要: Securing pods in a container orchestration environment is provided. A container runtime interface command is verified to perform an orchestration action on a set of containers comprising an application workload that corresponds to a service based on matching the container runtime interface command to a rule contained in a trusted execution environment contract included in a pod sandbox virtual machine of a trusted execution environment. It is determined whether the container runtime interface command to perform the orchestration action on the set of containers is valid based finding a matching rule in the trusted execution environment contract. In response to determining that the container runtime interface command to perform the orchestration action on the set of containers is valid, the container runtime interface command is executed to perform the orchestration action on the set of containers in the pod sandbox virtual machine of the trusted execution environment.

    IDENTIFYING SOFTWARE AND HARDWARE BOTTLENECKS

    公开(公告)号:US20200065077A1

    公开(公告)日:2020-02-27

    申请号:US16106456

    申请日:2018-08-21

    IPC分类号: G06F8/41 G06F9/52 G06F17/30

    摘要: A method is provided for building calling context trees of an application to identify a thread or a device affecting a throughput of a transaction relating to the application. The method obtains profiles of call stacks of multiple threads. The method obtains wake-up profiles which are the call stacks of a notifier thread and a waiter thread, from among the multiple threads, in a case that the waiter thread leaves from a sleep state. The method builds the calling context trees to indicate transitions of methods tracing callee relations and wake-up relations based on the profiles of the call stacks and the wake-up profiles, wherein each method is represented by a node having an average thread number. The method extracts and displays tree portions which are transitively reachable from a calling context tree for the transaction and which include the thread or device affecting throughput.

    Parallel Execution Mechanism and Operating Method Thereof
    7.
    发明申请
    Parallel Execution Mechanism and Operating Method Thereof 审中-公开
    并行执行机制及其操作方法

    公开(公告)号:US20170024249A1

    公开(公告)日:2017-01-26

    申请号:US15287272

    申请日:2016-10-06

    IPC分类号: G06F9/48 G06F9/30 G06F3/06

    摘要: A thread priority control mechanism is provided which uses the completion event of the preceding transaction to raise the priority of the next transaction in the order of execution when the transaction status has been changed from speculative to non-speculative. In one aspect of the present invention, a thread-level speculation mechanism is provided which has content-addressable memory, an address register and a comparator for recording transaction footprints, and a control logic circuit for supporting memory synchronization instructions. This supports hardware transaction memory in detecting transaction conflicts. This thread-level speculation mechanism includes a priority up bit for recording an attribute operand in a memory synchronization instruction, a means for generating a priority up event when a thread wake-up event has occurred and the priority up bit is 1, and a means for preventing the CAM from storing the load/store address when the instruction is a non-transaction instruction.

    摘要翻译: 提供一种线程优先级控制机制,当事务状态从投机状态改变为非投机状态时,使用前一事务的完成事件以执行顺序提高下一事务的优先级。 在本发明的一个方面,提供一种线程级推测机制,其具有内容可寻址存储器,地址寄存器和用于记录事务占用的比较器,以及用于支持存储器同步指令的控制逻辑电路。 这支持硬件事务内存检测事务冲突。 该线程级推测机制包括用于在存储器同步指令中记录属性操作数的优先级上位;当线程唤醒事件发生并且优先级上升位为1时产生优先级上升事件的装置;以及装置 用于在指令是非事务指令时防止CAM存储加载/存储地址。

    Multi-layer autoscaling for a scale-up cloud server

    公开(公告)号:US11023348B2

    公开(公告)日:2021-06-01

    申请号:US15801878

    申请日:2017-11-02

    摘要: A computer-implemented scaling method, an apparatus, and a computer program product for detecting whether a performance of a system reaches a target performance are provided. The method includes scaling a layered software environment, including scaling a first layer software environment in the layered software environment in response to the performance of the system not reaching the target performance and scaling a second layer software environment that is above the first layer software environment in the layered software environment in response to the performance of the system not reaching the target performance despite the first layer software environment being scaled. The method also includes scaling hardware resources used for executing the layered software environment in the system in response to the performance of the system not reaching the target performance before scaling of the first layer software environment or after scaling of the second layer software environment.

    Identifying software and hardware bottlenecks

    公开(公告)号:US10970055B2

    公开(公告)日:2021-04-06

    申请号:US16106456

    申请日:2018-08-21

    摘要: A method is provided for building calling context trees of an application to identify a thread or a device affecting a throughput of a transaction relating to the application. The method obtains profiles of call stacks of multiple threads. The method obtains wake-up profiles which are the call stacks of a notifier thread and a waiter thread, from among the multiple threads, in a case that the waiter thread leaves from a sleep state. The method builds the calling context trees to indicate transitions of methods tracing callee relations and wake-up relations based on the profiles of the call stacks and the wake-up profiles, wherein each method is represented by a node having an average thread number. The method extracts and displays tree portions which are transitively reachable from a calling context tree for the transaction and which include the thread or device affecting throughput.