公开(公告)号：US20220019529A1

公开(公告)日：2022-01-20

申请号：US16933183

申请日：2020-07-20

Applicant: VMware, Inc.

Inventor： Wenguang Wang ,  Vamsi Gunturu

IPC: G06F12/06

Abstract: A logical map represents fragments from separate versions of a data object. Migration of data from a first (old) version to the second (new) version happens gradually, where write operations go to the new version of the data object. The logical map initially points to the old data object, but is updated to point to the portions of the new data object as write operations are performed on the new data object. A background migration copies data from the old data object to the new data object.

公开(公告)号：US20220019456A1

公开(公告)日：2022-01-20

申请号：US17013727

申请日：2020-09-07

Applicant: VMware, Inc.

Inventor： MOUNESH BADIGER ,  Wenguang Wang ,  Adrian Drzewiecki ,  Maxime Austruy ,  Satish Pudi

IPC: G06F9/455 ,  G06F12/1036 ,  G06F12/02

Abstract: Examples provide a method of communication between a client driver and a filesystem server. The client driver executes in a virtual machine (VM) and the filesystem server executes in a hypervisor. The method includes: allocating, by the client driver, shared memory in an address space of the VM for the communication; sending identification information for the shared memory from the client driver to the filesystem server through an inter-process communication channel between the client driver and the filesystem server; identifying, by the filesystem server in cooperation with a kernel of the hypervisor, the shared memory within an address space of the hypervisor, based on the identification information, to create a shared memory channel; sending commands from the client driver to the filesystem server through the shared memory channel; and receiving completion messages for the commands from the filesystem server to the client driver through the shared memory channel.

公开(公告)号：US11226760B2

公开(公告)日：2022-01-18

申请号：US16842604

申请日：2020-04-07

Applicant: VMware, Inc.

Inventor： Wenguang Wang ,  Vamsi Gunturu

IPC: G06F3/06

Abstract: Techniques for supporting large segments when issuing writes to an erasure coded storage object in a distributed storage system are provided. In one set of embodiments, a node of the system can receive a write request for updating a logical data block of the storage object, write data/metadata for the block to a record in a data log of a metadata object of the storage object (where the metadata object is stored on a performance storage tier), and determine whether the data log has accumulated a threshold number of records. If so, the node can further allocate an in-memory bank, place the data from the data log records into free slots of the bank, allocate a segment in a capacity object of the storage object for holding contents of the bank (where the capacity object is stored on a capacity storage tier), and write the bank contents via a full stripe write to the allocated segment.

公开(公告)号：US20210311919A1

公开(公告)日：2021-10-07

申请号：US16842657

申请日：2020-04-07

Applicant: VMware, Inc.

Inventor： Wenguang Wang ,  Vamsi Gunturu ,  Eric Knauft

IPC: G06F16/215 ,  H04L29/08 ,  G06F16/23 ,  G06F12/0804

Abstract: Techniques for reducing data log recovery time and metadata write amplification when checkpointing a data log of a storage object in a distributed storage system are provided. In one set of embodiments, a node of the system can determine whether the data log has reached a first threshold size, where the data log comprises a plurality of data log records, and where each data log record includes data and metadata for a write request directed to the storage object. If the data log has reached the first threshold size, the node can copy, from each of the plurality of data log records, the metadata for the write request to a corresponding metadata log entry in a metadata log of the storage object. The node can then truncate the data log by removing the plurality of data log records.

公开(公告)号：US11093464B1

公开(公告)日：2021-08-17

申请号：US16857574

申请日：2020-04-24

Applicant: VMware, Inc.

Inventor： Wenguang Wang ,  Vamsi Gunturu

IPC: G06F16/00 ,  G06F16/215 ,  G06F16/22

Abstract: Solutions are disclosed for blocks in a multi-writer log-structured file system. Solutions include selecting candidate segments in a storage medium; reading blocks of the candidate segments; determining whether any blocks are duplicates; updating a reference count for the duplicate blocks; identifying unique blocks; writing at least a portion of the unique blocks to a log; determining whether the log has accumulated a full segment of data; based at least on determining that the log has accumulated a full segment of data, writing the full segment to the storage medium; updating a segment usage table (SUT) to mark the candidate segments as free; and updating the SUT to mark a segment of the storage medium as no longer free. Some examples identify a window start time and stop time, because older segments have been deduped and younger segments may be volatile. Some examples adjust the window to improve performance.

公开(公告)号：US11093450B2

公开(公告)日：2021-08-17

申请号：US15717704

申请日：2017-09-27

Applicant: VMware, Inc.

Inventor： Wenguang Wang ,  Abhishek Gupta ,  Richard P Spillane ,  Kapil Chowksey ,  Robert T Johnson

IPC: G06F16/13 ,  G06F16/17 ,  G06F3/06 ,  G06F16/14

Abstract: A Bε-tree associated with a file system on a storage volume includes a hierarchy of nodes. Each node includes a buffer portion to store key-value pairs as messages in the buffer. Each node can be characterized by having a maximum allowable size that is periodically updated at run time. The buffers in the nodes of the Bε-tree are therefore characterized by having a maximum allowed size that can vary over time.

公开(公告)号：US11093403B2

公开(公告)日：2021-08-17

申请号：US16209119

申请日：2018-12-04

Applicant: VMware, Inc.

Inventor： Wenguang Wang ,  Abhishek Srivastava ,  Ashish Kaila ,  Julien Freche

IPC: G06F12/0871

Abstract: The disclosure provides a technique for reducing cache misses to a cache of a computer system. The technique includes deallocating memory pages of the cache from one process and allocating those memory pages to another process based on cache misses of each process during a given time period. Repeating the technique leads the total number of cache misses to the cache to gradually decrease to an optimum or near optimum level. The repetition of the technique leads to a dynamic and flexible apportionment of cache memory pages to processes running within the computer system.

公开(公告)号：US11055265B2

公开(公告)日：2021-07-06

申请号：US16552880

申请日：2019-08-27

Applicant: VMware, Inc.

Inventor： Wenguang Wang ,  Junlong Gao ,  Marcos K. Aguilera ,  Richard P. Spillane ,  Christos Karamanolis ,  Maxime Austruy

IPC: G06F16/00 ,  G06F16/215 ,  G06F16/22

Abstract: The present disclosure provides techniques for scaling out deduplication of files among a plurality of nodes. The techniques include designating a master component for the coordination of deduplication. The master component divides files to be deduplicated among several slave nodes, and provides to each slave node a set of unique identifiers that are to be assigned to chunks during the deduplication process. The techniques herein preserve integrity of the deduplication process that has been scaled out among several nodes. The scaled out deduplication process deduplicates files faster by allowing several deduplication modules to work in parallel to deduplicate files.

公开(公告)号：US20210011855A1

公开(公告)日：2021-01-14

申请号：US16551761

申请日：2019-08-27

Applicant: VMware, Inc.

Inventor： KAMAL JEET CHARAN ,  Adrian Drzewiecki ,  Mounesh Badiger ,  Pushpesh Sharma ,  Wenguang Wang ,  Maxime Austruy ,  Richard P. Spillane

IPC: G06F12/1009 ,  G06F16/182 ,  G06F9/455

Abstract: A system and method for transferring data between a user space buffer in the address space of a user space process running on a virtual machine and a storage system are described The user space buffer is represented as a file with a file descriptor in the method, a file system proxy receives a request for I/O read or write from the user space process without copying data to be transferred. The file system proxy then sends the request to a file system server without copying data to be transferred. The file system server then requests that the storage system perform the requested I/O directly between the storage system and the user space buffer, the only transfer of data being between the storage system and the user space buffer.

公开(公告)号：US10552403B2

公开(公告)日：2020-02-04

申请号：US14719209

申请日：2015-05-21

Applicant: VMware, Inc.

Inventor： Wenguang Wang ,  Jorge Guerra Delgado

IPC: G03F7/00 ,  G06F16/23 ,  G06F16/28 ,  G06F11/20

Abstract: Techniques for reducing write latency when logging write operations are provided. In one embodiment, a computer system can receive a write operation originating from a storage client, where the write operation is directed to a data object stored on a nonvolatile storage of the computer system. The computer system can further calculate a checksum value based on the contents of the data object as modified by the write operation, and generate a log record for the write operation that includes the first checksum value and a pointer to a location of the data object on the nonvolatile storage. The computer system can then issue the write operation and a write of the log record concurrently to the nonvolatile storage, thereby reducing the latency incurred for the overall write/logging process before a write acknowledgement is sent to the storage client.