专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明授权

US11513970B2 Split virtual memory address loading mechanism 有权
公开(公告)号：US11513970B2
公开(公告)日：2022-11-29
申请号：US16671365
申请日：2019-11-01
申请人： International Business Machines Corporation
发明人： Juscelino Candido De Lima Junior , Breno H. Leitao , Carlos Eduardo Seo
IPC分类号： G06F12/00 , G06F12/1009 , G06F11/14 , G06F12/06
摘要： Virtual memory address space is divided according to areas of the virtual memory address and allocating some areas to low-cost volatile memory (such as RAM) when the memory areas are not required by an application to be stored in non-volatile memory, such as NVDIMM. A loader mechanism creates and maintains a layout address table in non-volatile memory for recovery from an unexpected reset.

2. 发明授权

US11086517B2 Page frame security 有权
公开(公告)号：US11086517B2
公开(公告)日：2021-08-10
申请号：US16174642
申请日：2018-10-30
申请人： INTERNATIONAL BUSINESS MACHINES CORPORATION
发明人： Breno H. Leitao , Juscelino Candido De Lima Junior , Carlos Eduardo Seo
IPC分类号： G06F3/06
摘要： Memory management that includes allocating physical memory having an append-only permission associated therewith to requesting user space applications is described. If a page frame is append-only, then data written to the page frame cannot be overwritten. Rather, any new data written to an append-only page frame must be written beginning at the next available write location within the page frame. An MMU determines whether a write request is requesting an append-only page frame, in which case, the MMU reserves the append-only page frame for the write request and consults a corresponding entry in a page table append to determine whether an offset associated with the write request is larger than a stored value in the entry that indicates the next available write location in the page frame. If so, the write request is executed and the data is written to the page frame beginning at the next available write location.

3. 发明授权

US10620959B2 Optimized multi-processor instruction scheduler 有权
公开(公告)号：US10620959B2
公开(公告)日：2020-04-14
申请号：US15828850
申请日：2017-12-01
申请人： International Business Machines Corporation
发明人： Rafael Camarda Silva Folco , Jose F. Santiago Filho , Desnes A. Nunes do Rosário , Breno H. Leitao
IPC分类号： G06F9/38 , G06F9/50 , G06F11/30 , G06F9/30
CPC分类号： G06F9/3836 , G06F9/30145 , G06F9/505 , G06F11/3003
摘要： In an approach for moving workloads between central processing units (CPUs) to accommodate balance, a processor profiles a first processor and a second processor of a plurality of processors, using a cycle per instruction metric. A processor assigns a first group of instructions to the first processor and a second group of instructions to the second processor. A processor sums an instruction count for the first group of instructions and an instruction count for the second group of instructions. A processor determines that a balance condition, defined by a predetermined threshold, does not exist across the first processor and the second processor. A processor identifies the second processor has a lower cycle per instruction metric than the first processor. A processor moves a workload, running on the first processor, with a maximum number of instructions of an unbalanced group to the second processor to balance workloads.

4. 发明申请

US20190332411A1 SEAMLESS VIRTUAL MACHINE HALT AND RESTART ON A SERVER 审中-公开
公开(公告)号：US20190332411A1
公开(公告)日：2019-10-31
申请号：US15964608
申请日：2018-04-27
申请人： International Business Machines Corporation
发明人： Breno H. Leitao , Rafael Camarda Silva Folco , Juscelino Candido De Lima Junior
IPC分类号： G06F9/455
摘要： Managing seamless server halt and restart is provided. A suspend event corresponding to a non-non-volatile dual-inline memory module (non-NVDIMM) server that comprises a set of virtual machines is received. In response to receiving the suspend event corresponding to the non-NVDIMM server, running virtual machine processes are stopped on the non-NVDIMM server. Virtual machine state information corresponding to stopped non-NVDIMM server virtual machine processes is saved on a set of non-volatile dual-inline memory modules (NVDIMMs) located in a non-volatile dual-inline memory module (NVDIMM) server.

5. 发明申请

US20190243561A1 BANDWIDTH MANAGEMENT OF MEMORY THROUGH CONTAINERS 审中-公开
公开(公告)号：US20190243561A1
公开(公告)日：2019-08-08
申请号：US16390136
申请日：2019-04-22
申请人： INTERNATIONAL BUSINESS MACHINES CORPORATION
发明人： Daniel Battaiola Kreling , Rafael Camarda Silva Folco , Breno H. Leitao , Mauro Sergio Martins Rodrigues
IPC分类号： G06F3/06
CPC分类号： G06F3/0613 , G06F3/0659 , G06F3/0673
摘要： Embodiments of the present invention disclose a method, computer program product, and system for managing memory bandwidth usage in software containers. Software container properties are received from a software container engine. In response to detecting the execution of one or more software containers by the software container engine, a monitoring layer is generated. At periodic time intervals, the generated monitoring layer monitors a memory bandwidth use value associated with each of the executed software containers. For each periodic time interval, an average memory use value is calculated, associated with each executed software container. In response to the calculated average memory use value being above a threshold associated with a monitored software container of the executed containers, the monitored software container is suspended for a suspend time duration. The suspended monitored software container is reactivated based on the suspend time duration expiring.

6. 发明授权

US10338824B2 Bandwidth management of memory through containers 有权
公开(公告)号：US10338824B2
公开(公告)日：2019-07-02
申请号：US15807758
申请日：2017-11-09
申请人： INTERNATIONAL BUSINESS MACHINES CORPORATION
发明人： Daniel Battaiola Kreling , Rafael Camarda Silva Folco , Breno H. Leitao , Mauro Sergio Martins Rodrigues
IPC分类号： G06F3/06
摘要： Embodiments of the present invention disclose a method, computer program product, and system for managing memory bandwidth usage in software containers. Software container properties are received from a software container engine. In response to detecting the execution of one or more software containers by the software container engine, a monitoring layer is generated. At periodic time intervals, the generated monitoring layer monitors a memory bandwidth use value associated with each of the executed software containers. For each periodic time interval, an average memory use value is calculated, associated with each executed software container. In response to the calculated average memory use value being above a threshold associated with a monitored software container of the executed containers, the monitored software container is suspended for a suspend time duration. The suspended monitored software container is reactivated based on the suspend time duration expiring.

7. 发明授权

US09396100B2 Software testing optimizer 有权
标题翻译：软件测试优化器
公开(公告)号：US09396100B2
公开(公告)日：2016-07-19
申请号：US14561445
申请日：2014-12-05
申请人： International Business Machines Corporation
发明人： Tiago N. dos Santos , Rafael C. S. Folco , Breno H. Leitao
IPC分类号： G06F9/44 , G06F11/36
CPC分类号： G06F11/3668 , G06F11/008 , G06F11/3688
摘要： In an approach for testing software, a computer receives a series of two or more revisions to a set of software code. The computer identifies modifications between the series of two or more revisions. The computer categorizes the series of two or more revisions into one or more categories of revisions based on the identified modifications. The computer tests at least one of the series of two or more revisions from at least one of the one or more categories of revisions.
摘要翻译：在一种测试软件的方法中，计算机接收一组软件代码的两个或多个修订版本。计算机识别一系列两个或多个修订版本之间的修改。计算机基于所识别的修改将两个或多个修订版本的一系列分类为一个或多个修订版本。该计算机至少从一个或多个修订类别中的至少一个对两个或更多个修订版本中的至少一个进行了测试。

8. 发明授权

US09170976B2 Network efficiency and power savings 有权
标题翻译：网络效率和功耗
公开(公告)号：US09170976B2
公开(公告)日：2015-10-27
申请号：US13733542
申请日：2013-01-03
申请人： International Business Machines Corporation
发明人： Rafael C. S. Folco , Breno H. Leitao , Tiago N. D. Santos
IPC分类号： G06F1/32 , G06F13/42
CPC分类号： G06F13/4295 , G06F1/3209 , G06F1/3287 , H04L43/0876 , H04L43/0888 , H04L43/16 , H04L47/783 , Y02D10/14 , Y02D10/151
摘要： A mechanism is provided for resource management. A first network interface card in a set of network interface cards receives network data from one or more servers in a set of servers. Responsive to the first network interface card determining that a first threshold has been met indicating that an overload condition is imminent in the first network interface card, the first network interface card sends a resume signal to a second network interface card in the set of network interface cards. Responsive to the first network interface card determining that a second threshold is being met indicating that the overload condition has been met in the first network interface card, the first network interface card delegates the network data that caused the overload condition to be met to the second interface card.
摘要翻译：为资源管理提供了一种机制。一组网络接口卡中的第一个网络接口卡从一组服务器中的一个或多个服务器接收网络数据。响应于第一网络接口卡确定已经满足表示第一网络接口卡中的过载状况的第一阈值，第一网络接口卡向网络接口集中的第二网络接口卡发送恢复信号牌。响应于第一网络接口卡确定正在满足第二阈值以指示在第一网络接口卡中满足过载条件，第一网络接口卡将导致满足的过载条件的网络数据委托给第二网络接口卡接口卡

9. 发明申请

US20140373010A1 INTELLIGENT RESOURCE MANAGEMENT FOR VIRTUAL MACHINES 审中-公开
标题翻译：虚拟机智能资源管理
公开(公告)号：US20140373010A1
公开(公告)日：2014-12-18
申请号：US13917727
申请日：2013-06-14
申请人： International Business Machines Corporation
发明人： Rafael C.S. Folco , Breno H. Leitao , Tiago N. dos Santos
IPC分类号： G06F9/50 , G06F9/455
CPC分类号： G06F9/45533 , G06F9/5077 , G06F9/5083
摘要： Embodiments of the present invention disclose a method, computer program product, and system for resource management for virtual machines. A computer receives information associated with one or more virtual machines, wherein the received information includes utilization information and workload information associated with each virtual machine of the one or more virtual machines. The computer analyzes the received information associated with the one or more virtual machines. The computer determines virtual machines for resource reallocation, wherein the determined virtual machines include one or more over-utilized virtual machines including at least one over-utilized resource. In another embodiment, the computer determines one or more under-utilized virtual machines, wherein the one or more under-utilized virtual machines include at least one under-utilized resource that corresponds to the determined one or more over-utilized resources. In another embodiment, the computer reallocates resources of the determined virtual machines for resource reallocation.
摘要翻译：本发明的实施例公开了一种用于虚拟机的资源管理方法，计算机程序产品和系统。计算机接收与一个或多个虚拟机相关联的信息，其中所接收的信息包括与所述一个或多个虚拟机的每个虚拟机相关联的利用信息和工作负载信息。计算机分析与一个或多个虚拟机相关联的接收到的信息。计算机确定用于资源重新分配的虚拟机，其中所确定的虚拟机包括一个或多个过度利用的虚拟机，其包括至少一个过度利用的资源。在另一个实施例中，计算机确定一个或多个未充分利用的虚拟机，其中一个或多个未充分利用的虚拟机包括对应于所确定的一个或多个过度利用的资源的至少一个未充分利用的资源。在另一个实施例中，计算机重新分配所确定的虚拟机的资源以用于资源重新分配。

10. 发明申请

US20140189173A1 Network Efficiency and Power Savings 有权
标题翻译：网络效率和节能
公开(公告)号：US20140189173A1
公开(公告)日：2014-07-03
申请号：US13733542
申请日：2013-01-03
申请人： INTERNATIONAL BUSINESS MACHINES CORPORATION
发明人： Rafael C. S. Folco , Breno H. Leitao , Tiago N. D. Santos
IPC分类号： G06F13/42
CPC分类号： G06F13/4295 , G06F1/3209 , G06F1/3287 , H04L43/0876 , H04L43/0888 , H04L43/16 , H04L47/783 , Y02D10/14 , Y02D10/151
摘要： A mechanism is provided for resource management. A first network interface card in a set of network interface cards receives network data from one or more servers in a set of servers. Responsive to the first network interface card determining that a first threshold has been met indicating that an overload condition is imminent in the first network interface card, the first network interface card sends a resume signal to a second network interface card in the set of network interface cards. Responsive to the first network interface card determining that a second threshold is being met indicating that the overload condition has been met in the first network interface card, the first network interface card delegates the network data that caused the overload condition to be met to the second interface card.
摘要翻译：为资源管理提供了一种机制。一组网络接口卡中的第一个网络接口卡从一组服务器中的一个或多个服务器接收网络数据。响应于第一网络接口卡确定已经满足表示第一网络接口卡中的过载状况的第一阈值，第一网络接口卡向网络接口集中的第二网络接口卡发送恢复信号牌。响应于第一网络接口卡确定正在满足第二阈值以指示在第一网络接口卡中满足过载条件，第一网络接口卡将导致满足的过载条件的网络数据委托给第二网络接口卡接口卡

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式