公开(公告)号：US10007546B2

公开(公告)日：2018-06-26

申请号：US15189130

申请日：2016-06-22

申请人： Mukund Gunti ,  Vishnu Sekhar ,  Rajesh Venkatasubramanian

发明人： Mukund Gunti ,  Vishnu Sekhar ,  Rajesh Venkatasubramanian

IPC分类号： G06F9/44 ,  G06F9/455 ,  G06F9/4401 ,  G06F8/656

CPC分类号： G06F9/45558 ,  G06F8/656 ,  G06F9/4406 ,  G06F2009/4557 ,  G06F2009/45575 ,  G06F2009/45583

摘要： An “old” hypervisor is upgraded to or otherwise replaced by a “new” hypervisor without migrating virtual machines to a standby computer. The old hypervisor partitions the computer that it controls between a source partition and a target partition. The hypervisor and its virtual machines initially run on the source partition, while a new hypervisor is installed on the target partition. The virtual machines are migrated to the new hypervisor without physically moving the in-memory virtual-machine data. Instead, the old hypervisor sends memory pointers, and the new hypervisor claims the respective memory locations storing the virtual-machine data. After all virtual machines are migrated, the old hypervisor bequeaths the hypervisor memory and a last processor that the old hypervisor requires to run. The new hypervisor claims the bequeathed processor and hypervisor memory after the old hypervisor terminates to complete the upgrade/exchange.

公开(公告)号：US08694728B2

公开(公告)日：2014-04-08

申请号：US12942765

申请日：2010-11-09

申请人： Carl A. Waldspurger ,  Rajesh Venkatasubramanian ,  Alexander Thomas Garthwaite ,  Yury Baskakov ,  Puneet Zaroo

发明人： Carl A. Waldspurger ,  Rajesh Venkatasubramanian ,  Alexander Thomas Garthwaite ,  Yury Baskakov ,  Puneet Zaroo

IPC分类号： G06F12/00

CPC分类号： G06F12/122 ,  G06F9/45558 ,  G06F11/3471 ,  G06F12/123 ,  G06F2009/45583 ,  G06F2201/815 ,  G06F2201/88

摘要： Miss rate curves are constructed in a resource-efficient manner so that they can be constructed and memory management decisions can be made while the workloads are running. The resource-efficient technique includes the steps of selecting a subset of memory pages for the workload, maintaining a least recently used (LRU) data structure for the selected memory pages, detecting accesses to the selected memory pages and updating the LRU data structure in response to the detected accesses, and generating data for constructing a miss-rate curve for the workload using the LRU data structure. After a memory page is accessed, the memory page may be left untraced for a period of time, after which the memory page is retraced.

摘要翻译： 错误率曲线以资源有效的方式构建，以便可以构建它们，并且可以在工作负载运行时进行内存管理决策。 资源有效的技术包括以下步骤：为工作负载选择存储器页面的子集，维护所选择的存储器页面的最近最少使用的（LRU）数据结构，检测对所选择的存储器页面的访问以及响应地更新LRU数据结构 并且使用LRU数据结构生成用于构建工作负载的错过率曲线的数据。 在访问存储器页面之后，存储器页面可以保持未被跟踪一段时间，之后再回读存储器页面。

公开(公告)号：US07925850B1

公开(公告)日：2011-04-12

申请号：US11676224

申请日：2007-02-16

申请人： Carl Waldspurger ,  Osten Kit Colbert ,  Xiaoxin Chen ,  Rajesh Venkatasubramanian

发明人： Carl Waldspurger ,  Osten Kit Colbert ,  Xiaoxin Chen ,  Rajesh Venkatasubramanian

IPC分类号： G06F12/00 ,  G06F13/00 ,  G06F13/28

CPC分类号： G06F9/4856

摘要： A system for increasing the efficiency of migrating, at least in part, a virtual machine from a source host to a destination host is described wherein the content of one or more portions of the address space of the virtual machine are each uniquely associated at the source host with a signature that may collide, absent disambiguation, with different content at the destination host. Code in both the source and destination hosts disambiguates the signature(s) so that each disambiguated signature may be uniquely associated with content at the destination host, and so that collisions with different content are avoided at the destination host. Logic is configured to determine whether the content uniquely associated with a disambiguated signature at the destination host is already present in the destination host memory, and, if so, to back one or more portions of the address space of the virtual machine having this content with one or more portions of the destination host memory already holding this content.

摘要翻译： 描述了一种用于提高至少部分地将虚拟机从源主机迁移到目的地主机的效率的系统，其中虚拟机的地址空间的一个或多个部分的内容每个在源处唯一地相关联 主机具有可能与目标主机不同的内容相冲突的缺席消息。 源主机和目标主机中的代码消除签名，使得每个消歧签名可以与目的主机的内容唯一相关联，并且使得在目的主机处避免与不同内容的冲突。 逻辑被配置为确定目的地主机上与消歧签名唯一相关联的内容是否已经存在于目的主机存储器中，并且如果是，则将具有该内容的虚拟机的地址空间的一个或多个部分返回到 目的地主机存储器的一个或多个部分已经保存该内容。

公开(公告)号：US10445123B2

公开(公告)日：2019-10-15

申请号：US15189108

申请日：2016-06-22

申请人： Xavier Deguillard ,  Mukund Gunti ,  Adrian Drzewiecki ,  Rajesh Venkatasubramanian

发明人： Xavier Deguillard ,  Mukund Gunti ,  Adrian Drzewiecki ,  Rajesh Venkatasubramanian

IPC分类号： G06F3/06 ,  G06F8/656 ,  G06F9/455 ,  G06F9/4401

摘要： A hypervisor exchange, e.g., an upgrade, can include consolidating resident virtual machines into a single host virtual machine, exchanging an old hypervisor with a new (upgraded) hypervisor, and disassociating the virtual resident virtual machines by migrating them to the new hypervisor. The consolidating can involve migrating the resident virtual machines from the old hypervisor to a guest hypervisor on the host virtual machine. The exchange can involve: 1) suspending the host virtual machine before the exchange; and 2) resuming the host virtual machine after the exchange; or migrating the host virtual machine from a partition including the old hypervisor to a partition hosting the new hypervisor. Either way, an exchange (upgrade) is achieve without requiring a bandwidth consuming migration over a network to a standby machine.

公开(公告)号：US20170371691A1

公开(公告)日：2017-12-28

申请号：US15189115

申请日：2016-06-22

申请人： Mukund Gunti ,  Vishnu Sekhar ,  Rajesh Venkatasubramanian

发明人： Mukund Gunti ,  Vishnu Sekhar ,  Rajesh Venkatasubramanian

IPC分类号： G06F9/455 ,  G06F12/109 ,  G06F3/06

摘要： A hypervisor-exchange process includes: suspending, by an “old” hypervisor, resident virtual machines; exchanging the old hypervisor for a new hypervisor, and resuming, by the new hypervisor, the resident virtual machines. The suspending can include “in-memory” suspension of the virtual machines until the virtual machines are resumed by the new hypervisor. Thus, there is no need to load the virtual machines from storage prior to the resuming. As a result, any interruption of the virtual machines is minimized. In some embodiments, the resident virtual machines are migrated onto one or more host virtual machines to reduce the number of virtual machines being suspended.

公开(公告)号：US20160306649A1

公开(公告)日：2016-10-20

申请号：US15189130

申请日：2016-06-22

申请人： Mukund Gunti ,  Vishnu Sekhar ,  Rajesh Venkatasubramanian

发明人： Mukund Gunti ,  Vishnu Sekhar ,  Rajesh Venkatasubramanian

IPC分类号： G06F9/455 ,  G06F9/50 ,  G06F12/02

CPC分类号： G06F9/45558 ,  G06F8/656 ,  G06F9/4406 ,  G06F2009/4557 ,  G06F2009/45575 ,  G06F2009/45583

摘要： An “old” hypervisor is upgraded to or otherwise replaced by a “new” hypervisor without migrating virtual machines to a standby computer. The old hypervisor partitions the computer that it controls between a source partition and a target partition. The hypervisor and its virtual machines initially run on the source partition, while a new hypervisor is installed on the target partition. The virtual machines are migrated to the new hypervisor without physically moving the in-memory virtual-machine data. Instead, the old hypervisor sends memory pointers, and the new hypervisor claims the respective memory locations storing the virtual-machine data. After all virtual machines are migrated, the old hypervisor bequeaths the hypervisor memory and a last processor that the old hypervisor requires to run. The new hypervisor claims the bequeathed processor and hypervisor memory after the old hypervisor terminates to complete the upgrade/exchange.

摘要翻译： “旧”虚拟机管理程序升级或替换为“新的”管理程序，而不会将虚拟机迁移到备用计算机。 旧的虚拟机管理程序将分区它在源分区和目标分区之间控制的计算机。 管理程序及其虚拟机最初在源分区上运行，而目标分区上安装了一个新的虚拟机管理程序。 虚拟机将迁移到新的管理程序，而不会物理移动内存中的虚拟机数据。 相反，旧的管理程序发送存储器指针，并且新的管理程序声明存储虚拟机数据的相应存储器位置。 在迁移所有虚拟机之后，旧的虚拟机管理程序将驻留管理程序内存和旧管理程序运行所需的最后一个处理器。 新的虚拟机管理程序在旧虚拟机管理程序终止后，要求遗留处理器和管理程序内存，以完成升级/更换。

公开(公告)号：US09135171B2

公开(公告)日：2015-09-15

申请号：US12834962

申请日：2010-07-13

申请人： Yury Baskakov ,  Alexander Thomas Garthwaite ,  Jesse Pool ,  Carl A. Waldspurger ,  Rajesh Venkatasubramanian ,  Ishan Banerjee

发明人： Yury Baskakov ,  Alexander Thomas Garthwaite ,  Jesse Pool ,  Carl A. Waldspurger ,  Rajesh Venkatasubramanian ,  Ishan Banerjee

IPC分类号： G06F12/00 ,  G06F12/08 ,  G06F11/14 ,  G06F12/10 ,  G06F9/455

CPC分类号： G06F12/08 ,  G06F11/1448 ,  G06F12/10 ,  G06F2009/45583 ,  G06F2212/151 ,  G06F2212/401 ,  G06F2221/0782

摘要： Page data of a virtual machine is represented for efficient save and restore operations. One form of representation applies to each page with an easily identifiable pattern. The page is described, saved, and restored in terms of metadata reflective of the pattern rather than a complete page of data reflecting the pattern. During a save or restore operation, however, the metadata of the page is represented, but not the page data. Another form of representation applies to each page sharing a canonical instance of a complex pattern that is instantiated in memory during execution, and explicitly saved and restored. Each page sharing the canonical page is saved and restored as a metadata reference, without the need to actually save redundant copies of the page data.

摘要翻译： 虚拟机的页面数据被表示为有效的保存和恢复操作。 一种形式的表示适用于每个页面，具有容易识别的模式。 根据反映模式的元数据来描述，保存和恢复页面，而不是反映模式的完整数据页面。 然而，在保存或恢复操作期间，表示页面的元数据，而不是页面数据。 另一种形式的表示适用于共享在执行期间在内存中实例化的复杂模式的规范实例的每个页面，并显式地保存和恢复。 共享规范页面的每个页面将作为元数据引用进行保存和恢复，而无需实际保存页面数据的冗余副本。

公开(公告)号：US20120017027A1

公开(公告)日：2012-01-19

申请号：US12834962

申请日：2010-07-13

申请人： Yury BASKAKOV ,  Alexander Thomas GARTHWAITE ,  Jesse POOL ,  Carl A. WALDSPURGER ,  Rajesh VENKATASUBRAMANIAN ,  Ishan BANERJEE

发明人： Yury BASKAKOV ,  Alexander Thomas GARTHWAITE ,  Jesse POOL ,  Carl A. WALDSPURGER ,  Rajesh VENKATASUBRAMANIAN ,  Ishan BANERJEE

IPC分类号： G06F12/10 ,  G06F12/08 ,  G06F12/00

CPC分类号： G06F12/08 ,  G06F11/1448 ,  G06F12/10 ,  G06F2009/45583 ,  G06F2212/151 ,  G06F2212/401 ,  G06F2221/0782

摘要： Page data of a virtual machine is represented for efficient save and restore operations. One form of representation applies to each page with an easily identifiable pattern. The page is described, saved, and restored in terms of metadata reflective of the pattern rather than a complete page of data reflecting the pattern. During a save or restore operation, however, the metadata of the page is represented, but not the page data. Another form of representation applies to each page sharing a canonical instance of a complex pattern that is instantiated in memory during execution, and explicitly saved and restored. Each page sharing the canonical page is saved and restored as a metadata reference, without the need to actually save redundant copies of the page data.

摘要翻译： 虚拟机的页面数据被表示为有效的保存和恢复操作。 一种形式的表示适用于每个页面，具有容易识别的模式。 根据反映模式的元数据来描述，保存和恢复页面，而不是反映模式的完整数据页面。 然而，在保存或恢复操作期间，表示页面的元数据，而不是页面数据。 另一种形式的表示适用于共享在执行期间在内存中实例化的复杂模式的规范实例的每个页面，并显式地保存和恢复。 共享规范页面的每个页面将作为元数据引用进行保存和恢复，而无需实际保存页面数据的冗余副本。

公开(公告)号：US20090313445A1

公开(公告)日：2009-12-17

申请号：US12137351

申请日：2008-06-11

申请人： Vivek Pandey ,  Ole Agesen ,  Alex Garthwaite ,  Carl Waldspurger ,  Rajesh Venkatasubramanian

发明人： Vivek Pandey ,  Ole Agesen ,  Alex Garthwaite ,  Carl Waldspurger ,  Rajesh Venkatasubramanian

IPC分类号： G06F13/00 ,  G06F12/00 ,  G06F9/455 ,  G06F12/16

CPC分类号： G06F9/5033 ,  G06F9/45558 ,  G06F9/4856 ,  G06F2009/4557

摘要： A system and related method of operation for migrating the memory of a virtual machine from one NUMA node to another. Once the VM is migrated to a new node, migration of memory pages is performed while giving priority to the most utilized pages, so that access to these pages becomes local as soon as possible. Various heuristics are described to enable different implementations for different situations or scenarios.

摘要翻译： 将虚拟机的存储器从一个NUMA节点迁移到另一个NUMA节点的系统和相关操作方法。 一旦将VM迁移到新节点，就会在优先使用最多的页面的同时执行内存页面的迁移，以便尽快访问这些页面。 描述了各种启发式方法，以实现不同情况或场景的不同实现。

公开(公告)号：US20160306648A1

公开(公告)日：2016-10-20

申请号：US15189108

申请日：2016-06-22

申请人： Xavier Deguillard ,  Mukund Gunti ,  Adrian Drzewiecki ,  Rajesh Venkatasubramanian

发明人： Xavier Deguillard ,  Mukund Gunti ,  Adrian Drzewiecki ,  Rajesh Venkatasubramanian

IPC分类号： G06F9/455 ,  G06F3/06

CPC分类号： G06F9/45558 ,  G06F3/0607 ,  G06F3/061 ,  G06F3/0644 ,  G06F3/0647 ,  G06F3/0664 ,  G06F3/0673 ,  G06F8/656 ,  G06F9/4406 ,  G06F2009/4557 ,  G06F2009/45575

摘要： A hypervisor exchange, e.g., an upgrade, can include consolidating resident virtual machines into a single host virtual machine, exchanging an old hypervisor with a new (upgraded) hypervisor, and disassociating the virtual resident virtual machines by migrating them to the new hypervisor. The consolidating can involve migrating the resident virtual machines from the old hypervisor to a guest hypervisor on the host virtual machine. The exchange can involve: 1) suspending the host virtual machine before the exchange; and 2) resuming the host virtual machine after the exchange; or migrating the host virtual machine from a partition including the old hypervisor to a partition hosting the new hypervisor. Either way, an exchange (upgrade) is achieve without requiring a bandwidth consuming migration over a network to a standby machine.

摘要翻译： 虚拟机管理程序交换（例如升级）可以包括将驻留的虚拟机整合到单个主机虚拟机中，与旧的（升级的）虚拟机管理程序交换旧的虚拟机管理程序，以及通过将虚拟驻留虚拟机迁移到新的管理程序来解除虚拟驻留虚拟机。 整合可以涉及将驻留的虚拟机从旧虚拟机管理程序迁移到主机虚拟机上的客户机管理程序。 交换可能涉及：1）在交换之前挂起主机虚拟机; 和2）交换后恢复主机虚拟机; 或将主机虚拟机从包含旧管理程序的分区迁移到托管新管理程序的分区。 无论哪种方式，都可实现交换（升级），而不需要通过网络迁移到备用计算机的带宽消耗。