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：US20210397480A1

公开(公告)日：2021-12-23

申请号：US17466185

申请日：2021-09-03

Applicant: VMware, Inc.

Inventor： Zhelong Pan ,  Rajesh Venkatasubramanian ,  Julien Freche ,  Prashanth Victor

IPC: G06F9/50

Abstract: Various examples are disclosed for cluster resource management using adaptive memory demands. In some examples, a local memory estimate is determined for a workload. The local memory estimate is determined using a memory reclamation parameter for the workload executed by a current host of the workload. A destination memory estimate is also determined for the workload. The destination memory estimate is determined using a full memory estimate unreduced by memory reclamation parameters. The workload is executed using a host that is selected in view of an analysis that uses the local memory estimate for the current host and the destination memory estimate for at least one destination host.

公开(公告)号：US11113109B2

公开(公告)日：2021-09-07

申请号：US16742111

申请日：2020-01-14

Applicant: VMware, Inc.

Inventor： Zhelong Pan ,  Rajesh Venkatasubramanian ,  Julien Freche ,  Prashanth Victor

IPC: G06F9/50

Abstract: Various examples are disclosed for cluster resource management using adaptive memory demands. Some aspects involve determining a destination memory estimate and a local memory estimate for various workloads executing in a datacenter. Goodness scores are determined corresponding to the candidate workload being executed on a number of different hosts. The goodness scores are determined using the local memory estimates for the currently executing workloads, the destination memory estimate is utilized for the candidate workload if it is not executing on the corresponding host. The workloads are balanced based on the goodness scores.

公开(公告)号：US11029863B2

公开(公告)日：2021-06-08

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 ,  G06F13/16 ,  G06F12/02 ,  G06F12/08 ,  G06F11/34 ,  G06F9/455 ,  G06F13/12 ,  G11C29/52 ,  G06F21/87 ,  G06F11/10

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：US20210216372A1

公开(公告)日：2021-07-15

申请号：US16742111

申请日：2020-01-14

Applicant: VMware, Inc.

Inventor： Zhelong Pan ,  Rajesh Venkatasubramanian ,  Julien Freche ,  Prashanth Victor

IPC: G06F9/50

Abstract: Various examples are disclosed for cluster resource management using adaptive memory demands. Some aspects involve determining a destination memory estimate and a local memory estimate for various workloads executing in a datacenter. Goodness scores are determined corresponding to the candidate workload being executed on a number of different hosts. The goodness scores are determined using the local memory estimates for the currently executing workloads, the destination memory estimate is utilized for the candidate workload if it is not executing on the corresponding host. The workloads are balanced based on the goodness scores.

公开(公告)号：US20200133846A1

公开(公告)日：2020-04-30

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: 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：US20190171390A1

公开(公告)日：2019-06-06

申请号：US15830850

申请日：2017-12-04

Applicant: VMware, Inc.

Inventor： Julien Freche ,  Kiran Tati ,  Rajesh Venkatasubramanian

IPC: G06F3/06

Abstract: Hierarchical resource tree memory operations can include receiving, at a memory scheduler, an indication of a proposed modification to a value of a memory parameter of an object represented by a node of a hierarchical resource tree, wherein the proposed modification is made by a modifying entity, locking the node of the hierarchical resource tree by the memory scheduler, performing the proposed modification by the memory scheduler, wherein performing the proposed modification includes creating a working value of the memory parameter according to the proposed modification, determining whether the proposed modification violates a structural consistency of the hierarchical resource tree based on the working value, and replacing the value of the memory parameter with the working value of the memory parameter in response to determining that the proposed modification does not violate a structural consistency of the hierarchical resource tree based on the working value, and unlocking the node of the hierarchical resource tree by the memory scheduler.

公开(公告)号：US11669369B2

公开(公告)日：2023-06-06

申请号：US17466185

申请日：2021-09-03

Applicant: VMware, Inc.

Inventor： Zhelong Pan ,  Rajesh Venkatasubramanian ,  Julien Freche ,  Prashanth Victor

IPC: G06F9/50

CPC classification number: G06F9/5016 ,  G06F9/505 ,  G06F2209/5022

Abstract: Various examples are disclosed for cluster resource management using adaptive memory demands. In some examples, a local memory estimate is determined for a workload. The local memory estimate is determined using a memory reclamation parameter for the workload executed by a current host of the workload. A destination memory estimate is also determined for the workload. The destination memory estimate is determined using a full memory estimate unreduced by memory reclamation parameters. The workload is executed using a host that is selected in view of an analysis that uses the local memory estimate for the current host and the destination memory estimate for at least one destination host.

公开(公告)号：US20220129377A1

公开(公告)日：2022-04-28

申请号：US17571417

申请日：2022-01-07

Applicant: VMware, Inc.

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

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

Abstract: Techniques for efficiently purging non-active blocks in an NVM region of an NVM device using virtblocks are provided. In one set of embodiments, a host system can maintain, in the NVM device, a pointer entry (i.e., virtblock entry) for each allocated data block of the NVM region, where page table entries of the NVM region that refer to the allocated data block include pointers to the pointer entry, and where the pointer entry includes a pointer to the allocated data block. The host system can further determine that a subset of the allocated data blocks of the NVM region are non-active blocks and can purge the non-active blocks from the NVM device to a mass storage device, where the purging comprises updating the pointer entry for each non-active block to point to a storage location of the non-active block on the mass storage device.