公开(公告)号：US11409705B2

公开(公告)日：2022-08-09

申请号：US16517436

申请日：2019-07-19

Applicant: VMware, Inc.

Inventor： William Earl ,  Christos Karamanolis ,  Kiran Joshi

IPC: G06F16/17 ,  G06F11/14

Abstract: Embodiments of the disclosure provide techniques managing a log-structured solid state drive (SSD) format in a distributed storage system. SSDs in the distributed storage system maintains a journal of logical changes to storage objects to persist prepared and committed changes in the latency path. The journal includes metadata entries that describe changes and reference data pages. Dense data structures (such as a logical block addressing table) index the metadata entries. To reduce the amount of overhead in I/O operations, the distributed storage system maintains the dense data structures in memory rather than on disk.

公开(公告)号：US11182344B2

公开(公告)日：2021-11-23

申请号：US15068988

申请日：2016-03-14

Applicant: VMware, Inc.

Inventor： Edward J Goggin ,  Sandeep Rangaswamy ,  Kiran Joshi ,  Srinath Premachandran ,  Gopala Suryanarayana ,  Radu Berinde ,  Wenguang Wang ,  Jorge Guerra Delgado ,  Jin Zhang ,  Radhika Vullikanti

IPC: G06F16/00 ,  G06F16/174 ,  H04L29/08

Abstract: In accordance with the present disclosure, files may be deduplicated in a distributed storage system having a plurality of storage volumes. A uniqueness metric for each file may indicate a degree of deduplication of the respective data files in the given storage volume. The uniqueness metric may be used to identify files for rebalancing in the distributed storage system. The uniqueness metric may be efficiently calculated with enough accuracy using a sampling methodology.

公开(公告)号：US20200175074A1

公开(公告)日：2020-06-04

申请号：US16209965

申请日：2018-12-04

Applicant: VMware, Inc.

Inventor： Tan Li ,  Zhihao Yao ,  Sunil Satnur ,  Kiran Joshi

IPC: G06F16/901 ,  G06F12/0871 ,  G06F12/0891

Abstract: Nodes in tree data structure can be cached in a cache memory. When the cache memory becomes full, an eviction policy selects cached nodes based on their location in the tree data structure. The eviction policy selects cached nodes that correspond to leaf nodes in the tree data structure as candidates for eviction. The eviction policy selects cached nodes that correspond to internal (non-leaf) nodes from the lowest level possible for eviction, only if there are no cached leaf nodes.

公开(公告)号：US20200142828A1

公开(公告)日：2020-05-07

申请号：US16178515

申请日：2018-11-01

Applicant: VMware, Inc.

Inventor： Zhihao Yao ,  Tan Li ,  Sunil Satnur ,  Kiran Joshi

IPC: G06F12/084

Abstract: A shared cache memory can be logically partitioned among different workloads to provide isolation between workloads and avoid excessive resource contention. Each logical partition is apportioned a share of the cache memory, and is exclusive to a respective one of the workloads. Each partition has an initial size allocation. Historical data can be collected and processed for each partition and used to periodically update its size allocation.

公开(公告)号：US10402374B2

公开(公告)日：2019-09-03

申请号：US14469418

申请日：2014-08-26

Applicant: VMware, Inc.

Inventor： William Earl ,  Christos Karamanolis ,  Kiran Joshi

IPC: G06F11/14 ,  G06F16/17

Abstract: Embodiments of the disclosure provide techniques managing a log-structured solid state drive (SSD) format in a distributed storage system. SSDs in the distributed storage system maintains a journal of logical changes to storage objects to persist prepared and committed changes in the latency path. The journal includes metadata entries that describe changes and reference data pages. Dense data structures (such as a logical block addressing table) index the metadata entries. To reduce the amount of overhead in I/O operations, the distributed storage system maintains the dense data structures in memory rather than on disk.

公开(公告)号：US10102057B2

公开(公告)日：2018-10-16

申请号：US14716756

申请日：2015-05-19

Applicant: VMware, Inc.

Inventor： Christos Karamanolis ,  Wenguang Wang ,  Kiran Joshi ,  Sandeep Rangaswamy

IPC: G06F11/10 ,  H04L29/08 ,  G06F3/06 ,  H04L29/06

Abstract: Exemplary methods, apparatuses, and systems include a first layer of a virtual storage area network (VSAN) module receiving a write request from a data compute node. The write request includes data to be written and the VSAN module is distributed across a plurality of computers to provide an aggregate object store using storage attached to each of the plurality of computers. The first layer of the VSAN module calculates a checksum for the data to be written and passes the data to be written and the checksum to a second layer of the VSAN module. The second layer of the VSAN module calculates a first verification checksum for the data to be written. The data and the checksum are written to persistent storage in response to determining the first verification checksum matches the checksum passed by the first layer of the VSAN module.

公开(公告)号：US20170262465A1

公开(公告)日：2017-09-14

申请号：US15068988

申请日：2016-03-14

Applicant: VMware, Inc.

Inventor： Edward J. Goggin ,  Sandeep Rangaswamy ,  Kiran Joshi ,  Srinath Premachandran ,  Gopala Suryanarayana ,  Radu Berinde ,  Wenguang Wang ,  Jorge Guerra Delgado ,  Jin Zhang ,  Radhika Vullikanti

IPC: G06F17/30 ,  H04L29/08

CPC classification number: G06F16/1748 ,  H04L67/1004 ,  H04L67/1097

Abstract: In accordance with the present disclosure, files may be deduplicated in a distributed storage system having a plurality of storage volumes. A uniqueness metric for each file may indicate a degree of deduplication of the respective data files in the given storage volume. The uniqueness metric may be used to identify files for rebalancing in the distributed storage system. The uniqueness metric may be efficiently calculated with enough accuracy using a sampling methodology.

公开(公告)号：US20170199674A1

公开(公告)日：2017-07-13

申请号：US14993827

申请日：2016-01-12

Applicant: VMware, Inc.

Inventor： Jorge Guerra Delgado ,  Kiran Joshi ,  Edward J. Goggin ,  Srinath Premachandran ,  Sandeep Rangaswamy

IPC: G06F3/06

CPC classification number: G06F3/0608 ,  G06F3/0641 ,  G06F3/0665 ,  G06F3/0683

Abstract: Techniques for implementing data deduplication in conjunction with thick and thin provisioning of storage objects are provided. In one embodiment, a system can receive a write request directed to a storage object stored by the system and can determine whether the storage object is a thin or thick object. If the storage object is a thin object, the system can calculate a usage value by adding a total amount of physical storage space used in the system to a total amount of storage space reserved for thick storage objects in the system and further subtracting a total amount of reserved storage space for the thick storage objects that are filled with unique data. The system can then reject the write request if the usage value is not less than the total storage capacity of the system.

公开(公告)号：US09448728B2

公开(公告)日：2016-09-20

申请号：US14839163

申请日：2015-08-28

Applicant: VMware, Inc.

Inventor： Faraz Shaikh ,  Murali Vilayannur ,  Satyam B. Vaghani ,  Kiran Joshi

IPC: G06F3/06 ,  G06F17/30 ,  G06F9/455 ,  G06F12/02

CPC classification number: G06F3/0608 ,  G06F3/0631 ,  G06F3/0652 ,  G06F3/0665 ,  G06F3/067 ,  G06F9/45533 ,  G06F9/45558 ,  G06F12/0253 ,  G06F12/0261 ,  G06F12/0269 ,  G06F12/0276 ,  G06F17/30138 ,  G06F17/30194 ,  G06F17/30233 ,  G06F2009/45579 ,  G06F2212/1044 ,  G06F2212/154

Abstract: Free storage blocks previously allocated to a logical block device are released back to an underlying storage system supporting the logical block device in a manner that does not conflict with write operations that may be issued to the free storage blocks at about the same time. According to a first technique, write operations on the same storage blocks to be released are paused until the underlying storage system has completed the releasing operation or, if the write operations are issued earlier than when the underlying storage system actually performs the releasing operation, such storage blocks are not released. According to a second technique, a special file is allocated the free storage blocks, which are then made available for safe releasing.

公开(公告)号：US10747668B2

公开(公告)日：2020-08-18

申请号：US16178515

申请日：2018-11-01

Applicant: VMware, Inc.

Inventor： Zhihao Yao ,  Tan Li ,  Sunil Satnur ,  Kiran Joshi

IPC: G06F12/08 ,  G06F12/084

Abstract: A shared cache memory can be logically partitioned among different workloads to provide isolation between workloads and avoid excessive resource contention. Each logical partition is apportioned a share of the cache memory, and is exclusive to a respective one of the workloads. Each partition has an initial size allocation. Historical data can be collected and processed for each partition and used to periodically update its size allocation.