公开(公告)号：US10691591B2

公开(公告)日：2020-06-23

申请号：US16174264

申请日：2018-10-29

Applicant: VMware, Inc.

Inventor： Kiran Tati ,  Xavier Deguillard ,  Ishan Banerjee ,  Julien Freche ,  Preeti Agarwal ,  Rajesh Venkatasubramanian

IPC: G06F13/00 ,  G06F12/02 ,  G06F12/0804

Abstract: Techniques for efficiently purging non-active blocks in an NVM region of an NVM device using pointer elimination are provided. In one set of embodiments, a host system can, for each level 1 (L1) page table entry of each snapshot of the NVM region, determine whether a data block of the NVM region that is pointed to by the L1 page table entry is a non-active block, and if the data block is a non-active block, remove a pointer to the data block in the L1 page table entry and reduce a reference count parameter associated with the data block by 1. If the reference count parameter has reached zero at this point, the host system purge the data block from the NVM device to the mass storage device.

公开(公告)号：US20190065091A1

公开(公告)日：2019-02-28

申请号：US15693292

申请日：2017-08-31

Applicant: VMware, Inc.

Inventor： Kiran Tati ,  Preeti Agarwal ,  Julien Freche ,  Xavier Deguillard ,  Rajesh Venkatasubramanian ,  Ishan Banerjee

IPC: G06F3/06

Abstract: Techniques for using non-volatile random access memory (NVM) as volatile random access memory (RAM) are provided. In one set of embodiments, a computer system can detect that an amount of free space in a volatile RAM of the computer system has become low and, in response, can add one or more memory pages from an unused portion of an NVM of the computer system to the system's volatile RAM pool. Conversely, the computer system can detect that an amount of free space in the NVM has become low and, in response, can return the one or more memory pages from the volatile RAM pool back to the NVM.

公开(公告)号：US20180046581A1

公开(公告)日：2018-02-15

申请号：US15233337

申请日：2016-08-10

Applicant: VMware, Inc.

Inventor： Ishan Banerjee ,  Jui-Hao Chiang ,  Kiran Tati ,  Preeti Agarwal

IPC: G06F12/1009 ,  G06F11/07 ,  G06F3/06

CPC classification number: G06F12/1009 ,  G06F3/0611 ,  G06F3/0653 ,  G06F3/067 ,  G06F9/45533 ,  G06F9/45558 ,  G06F11/073 ,  G06F11/079 ,  G06F2009/45583 ,  G06F2009/45591 ,  G06F2212/1024 ,  G06F2212/1032 ,  G06F2212/152 ,  G06F2212/154

Abstract: Examples provide a page-fault latency feedback metric to determine performance of workloads or virtual machines (VMs) running on a VM host in a cluster. A hypervisor induces page-faults by varying a memory limit associated with a VM. Page-fault latencies are measured at each of the varying memory limits. A performance loss occurring at each page-fault latency is measured and converted to a performance score. A page-fault translation table is constructed based on the page-fault latencies and assigned performance scores. When a page-fault occurs during execution of a workload on a VM host in the cluster, a cluster manager maps the page-fault latency associated with the page-fault to a performance score in the page-fault translation table. The cluster manager computes a current workload performance or VM performance based on the page-fault latency and the performance score.

公开(公告)号：US09547510B2

公开(公告)日：2017-01-17

申请号：US14101787

申请日：2013-12-10

Applicant: VMware, Inc.

Inventor： Xavier Deguillard ,  Ishan Banerjee ,  Qasim Ali ,  Yury Baskakov ,  Kiran Tati ,  Rajesh Venkatasubramanian

IPC: G06F9/46 ,  G06F9/455 ,  G06F9/50

CPC classification number: G06F9/455 ,  G06F9/45558 ,  G06F9/50 ,  G06F9/5016 ,  G06F9/5077 ,  G06F12/08 ,  G06F2009/45583 ,  G06F2212/152 ,  G06F2212/401

Abstract: A system and method are disclosed for improving operation of a memory scheduler operating on a host machine supporting virtual machines (VMs) in which guest operating systems and guest applications run. For each virtual machine, the host machine hypervisor categorizes memory pages into memory usage classes and estimates the total number of pages for each memory usage class. The memory scheduler uses this information to perform memory reclamation and allocation operations for each virtual machine. The memory scheduler further selects between ballooning reclamation and swapping reclamation operations based in part on the numbers of pages in each memory usage class for the virtual machine. Calls to the guest operating system provide the memory usage class information. Memory reclamation not only can improve the performance of existing VMs, but can also permit the addition of a VM on the host machine without substantially impacting the performance of the existing and new VMs.

Abstract translation: 公开了一种系统和方法，用于改进在支持客机操作系统和来宾应用运行的虚拟机（VM）的主机上运行的存储器调度器的操作。 对于每个虚拟机，主机管理程序将内存页分为内存使用类，并估计每个内存使用类的总页数。 内存调度器使用该信息为每个虚拟机执行内存回收和分配操作。 存储器调度器还部分地基于虚拟机的每个存储器使用类别中的页数来选择气球回收和交换回收操作之间。 对客户机操作系统的调用提供了内存使用类信息。 内存回收不仅可以提高现有虚拟机的性能，还可以允许在主机上添加虚拟机，而不会对现有和新的虚拟机造成实质性的影响。

公开(公告)号：US11455182B2

公开(公告)日：2022-09-27

申请号：US16403033

申请日：2019-05-03

Applicant: VMware, Inc.

Inventor： Ishan Banerjee ,  Preeti Agarwal ,  Valeriy Zhuravlev ,  Nick M Ryan ,  Mohammed Junaid Ahmed

IPC: G06F9/455 ,  G06F12/1009 ,  G06F21/62

Abstract: Systems and methods are described for encrypting a swap file in a computer system. The swap file can be encrypted by a background process executing on the computer system. Processing of paging swapping operations occurs independently and separately of the background encryption of the swap file. Processing a page swapping operation can include decrypting or encrypting data to be swapped involved in the paging operation depending on the paging operation and whether or not the data to be swapped is encrypted or not.

公开(公告)号：US20200348954A1

公开(公告)日：2020-11-05

申请号：US16403033

申请日：2019-05-03

Applicant: VMware, Inc.

Inventor： Ishan Banerjee ,  Preeti Agarwal ,  Valeriy Zhuravlev ,  Nick M. Ryan ,  Mohammed Junaid Ahmed

IPC: G06F9/455 ,  G06F12/1009 ,  G06F21/62

Abstract: Systems and methods are described for encrypting a swap file in a computer system. The swap file can be encrypted by a background process executing on the computer system. Processing of paging swapping operations occurs independently and separately of the background encryption of the swap file. Processing a page swapping operation can include decrypting or encrypting data to be swapped involved in the paging operation depending on the paging operation and whether or not the data to be swapped is encrypted or not.

公开(公告)号：US10705954B2

公开(公告)日：2020-07-07

申请号：US16174270

申请日：2018-10-29

Applicant: VMware, Inc.

Inventor： Rajesh Venkatasubramanian ,  Ishan Banerjee ,  Julien Freche ,  Kiran Tati ,  Preeti Agarwal ,  Xavier Deguillard

IPC: G06F13/00 ,  G06F12/02 ,  G06F12/0804 ,  G06F12/1009

Abstract: Techniques for efficiently purging non-active blocks in an NVM region of an NVM device while preserving large pages are provided. In one set of embodiments, a host system can receive a write request with respect to a data block of the NVM region, where the data block is referred to by a snapshot of the NVM region and was originally allocated as part of a large page. The host system can further allocate a new data block in the NVM region, copy contents of the data block to the new data block, and update the data block with write data associated with the write request. The host system can then update a level 1 (L1) page table entry of the NVM region's running point to point to the original data block.

公开(公告)号：US20200133847A1

公开(公告)日：2020-04-30

申请号：US16174270

申请日：2018-10-29

Applicant: VMware, Inc.

Inventor： Rajesh Venkatasubramanian ,  Ishan Banerjee ,  Julien Freche ,  Kiran Tati ,  Preeti Agarwal ,  Xavier Deguillard

IPC: G06F12/02 ,  G06F12/0804 ,  G06F12/1009

Abstract: Techniques for efficiently purging non-active blocks in an NVM region of an NVM device while preserving large pages are provided. In one set of embodiments, a host system can receive a write request with respect to a data block of the NVM region, where the data block is referred to by a snapshot of the NVM region and was originally allocated as part of a large page. The host system can further allocate a new data block in the NVM region, copy contents of the data block to the new data block, and update the data block with write data associated with the write request. The host system can then update a level 1 (L1) page table entry of the NVM region's running point to point to the original data block.

公开(公告)号：US10083123B2

公开(公告)日：2018-09-25

申请号：US15233337

申请日：2016-08-10

Applicant: VMware, Inc.

Inventor： Ishan Banerjee ,  Jui-Hao Chiang ,  Kiran Tati ,  Preeti Agarwal

IPC: G06F12/1009 ,  G06F3/06 ,  G06F11/07 ,  G06F9/455

CPC classification number: G06F12/1009 ,  G06F3/0611 ,  G06F3/0653 ,  G06F3/067 ,  G06F9/45533 ,  G06F9/45558 ,  G06F11/073 ,  G06F11/079 ,  G06F11/3414 ,  G06F2009/45583 ,  G06F2009/45591 ,  G06F2212/1024 ,  G06F2212/1032 ,  G06F2212/152 ,  G06F2212/154

Abstract: Examples provide a page-fault latency feedback metric to determine performance of workloads or virtual machines (VMs) running on a VM host in a cluster. A hypervisor induces page-faults by varying a memory limit associated with a VM. Page-fault latencies are measured at each of the varying memory limits. A performance loss occurring at each page-fault latency is measured and converted to a performance score. A page-fault translation table is constructed based on the page-fault latencies and assigned performance scores. When a page-fault occurs during execution of a workload on a VM host in the cluster, a cluster manager maps the page-fault latency associated with the page-fault to a performance score in the page-fault translation table. The cluster manager computes a current workload performance or VM performance based on the page-fault latency and the performance score.

公开(公告)号：US09529609B2

公开(公告)日：2016-12-27

申请号：US14101796

申请日：2013-12-10

Applicant: VMware, Inc.

Inventor： Xavier DeGuillard ,  Ishan Banerjee ,  Qasim Ali ,  Yury Baskakov ,  Kiran Tati ,  Rajesh Venkatasubramanian

IPC: G06F9/46 ,  G06F9/455 ,  G06F9/50

CPC classification number: G06F9/455 ,  G06F9/45558 ,  G06F9/5016 ,  G06F9/5077 ,  G06F2009/45583 ,  G06F2212/152

Abstract: A system and method are disclosed for improving operation of a memory scheduler operating on a host machine supporting virtual machines (VMs) in which guest operating systems and guest applications run. For each virtual machine, the host machine hypervisor categorizes memory pages into memory usage classes and estimates the total number of pages for each memory usage class. The memory scheduler uses this information to perform memory reclamation and allocation operations for each virtual machine. The memory scheduler further selects between ballooning reclamation and swapping reclamation operations based in part on the numbers of pages in each memory usage class for the virtual machine. Calls to the guest operating system provide the memory usage class information. Memory reclamation not only can improve the performance of existing VMs, but can also permit the addition of a VM on the host machine without substantially impacting the performance of the existing and new VMs.

Abstract translation: 公开了一种系统和方法，用于改进在支持客机操作系统和来宾应用运行的虚拟机（VM）的主机上运行的存储器调度器的操作。 对于每个虚拟机，主机管理程序将内存页分为内存使用类，并估计每个内存使用类的总页数。 内存调度器使用该信息为每个虚拟机执行内存回收和分配操作。 存储器调度器还部分地基于虚拟机的每个存储器使用类别中的页数来选择气球回收和交换回收操作之间。 对客户机操作系统的调用提供了内存使用类信息。 内存回收不仅可以提高现有虚拟机的性能，还可以允许在主机上添加虚拟机，而不会对现有和新的虚拟机造成实质性的影响。