公开(公告)号：US20250117299A1

公开(公告)日：2025-04-10

申请号：US18982992

申请日：2024-12-16

Applicant: Nutanix, Inc.

Inventor： Anish Jain ,  Prakash Narayanasamy ,  Praveen Kumar Padia ,  Vivek Venkatesan ,  Niranjan Sanjiv Pendharkar ,  Shubham Sharma

IPC: G06F11/20

Abstract: A technique monitors input/output (I/O) and storage ownership takeover activity patterns to detect degraded performance of a highly available and fault tolerant application executing in a multi-site environment. Multiple instances of the application execute in different containers or pods running on virtual machines (VMs) of a compute layer within a containerized (e.g., Kubernetes) clustering configuration that extends across clusters of the sites. A storage layer of the clusters provides shared storage to the pods running on the VMs across the multiple sites. One of the sites is configured as an active storage site configured to receive and service I/O requests from the compute layer. A single instance of the application is active at a time and configured as a “compute owner” of the shared storage to issue the I/O requests to the shared storage. The compute owner and active storage site may not be co-located on the same site, leading to excessive I/O and storage ownership takeover activity patterns indicative of degraded performance. Upon detecting such patterns, the technique automatically triggers a storage failover to ensure that compute owner and active storage site are co-located at the same site.

公开(公告)号：US11575745B2

公开(公告)日：2023-02-07

申请号：US17184789

申请日：2021-02-25

Applicant: Nutanix, Inc.

Inventor： Kiran Tatiparthi ,  Niranjan Sanjiv Pendharkar ,  Shubham Sharma

IPC: H04L67/1095 ,  G06F9/455 ,  H04L67/1008

Abstract: A dynamic feedback technique improves data replication performance by balancing rates of data retrieval and data transmission of a fragmented virtual disk replicated between nodes of clusters on a local site and a remote site of a disaster recovery environment. Each node is embodied as a physical computer with hardware resources, such as processor, memory, network and storage resources, which are virtualized to provide support for one or more user virtual machines executing on the node. The storage resources include storage devices of an extent store, whereas the network includes a wide area network connecting the local and remote sites. The dynamic feedback technique employs a virtual memory buffer configured to balance the data storage retrieval and network transmission rates at a source of replication based on bandwidth demands of the extent store and network throughput as manifested by an available free space (i.e., emptiness) of the virtual buffer.

公开(公告)号：US20220217204A1

公开(公告)日：2022-07-07

申请号：US17184789

申请日：2021-02-25

Applicant: Nutanix, Inc.

Inventor： Kiran Tatiparthi ,  Niranjan Sanjiv Pendharkar ,  Shubham Sharma

IPC: H04L29/08 ,  G06F9/455

Abstract: A dynamic feedback technique improves data replication performance by balancing rates of data retrieval and data transmission of a fragmented virtual disk replicated between nodes of clusters on a local site and a remote site of a disaster recovery environment. Each node is embodied as a physical computer with hardware resources, such as processor, memory, network and storage resources, which are virtualized to provide support for one or more user virtual machines executing on the node. The storage resources include storage devices of an extent store, whereas the network includes a wide area network connecting the local and remote sites. The dynamic feedback technique employs a virtual memory buffer configured to balance the data storage retrieval and network transmission rates at a source of replication based on bandwidth demands of the extent store and network throughput as manifested by an available free space (i.e., emptiness) of the virtual buffer.

公开(公告)号：US12169445B2

公开(公告)日：2024-12-17

申请号：US18095271

申请日：2023-01-10

Applicant: Nutanix, Inc.

Inventor： Anish Jain ,  Niranjan Sanjiv Pendharkar ,  Praveen Kumar Padia ,  Shubham Sharma ,  Vivek Venkatesan

IPC: G06F11/00 ,  G06F11/07 ,  G06F11/20 ,  G06F11/30

Abstract: A technique monitors input/output (I/O) and Persistent Reservation (PR) activity patterns to detect degraded performance of a highly available and fault tolerant application executing in a multi-site disaster recovery (DR) environment. Multiple instances of the application execute in different virtual machines (VMs) of a compute layer within a guest clustering configuration that extends across clusters of the sites. A storage layer of the clusters provides shared storage to the multiple VMs across the multiple sites. One of the sites is configured as an active storage site configured to receive and service I/O requests from the compute layer. A single instance of the application is active at a time and configured as a “compute owner” of the shared storage to issue the I/O requests to the shared storage. The compute owner and active storage site may not be co-located on the same site, leading to excessive I/O and PR activity patterns indicative of degraded performance. Upon detecting such patterns, the technique automatically triggers a storage failover to ensure that compute owner and active storage site are co-located at the same site.

公开(公告)号：US20240143462A1

公开(公告)日：2024-05-02

申请号：US18095271

申请日：2023-01-10

Applicant: Nutanix, Inc.

Inventor： Anish Jain ,  Niranjan Sanjiv Pendharkar ,  Praveen Kumar Padia ,  Shubham Sharma ,  Vivek Venkatesan

IPC: G06F11/20 ,  G06F11/07 ,  G06F11/30

CPC classification number: G06F11/203 ,  G06F11/076 ,  G06F11/3075

Abstract: A technique monitors input/output (I/O) and Persistent Reservation (PR) activity patterns to detect degraded performance of a highly available and fault tolerant application executing in a multi-site disaster recovery (DR) environment. Multiple instances of the application execute in different virtual machines (VMs) of a compute layer within a guest clustering configuration that extends across clusters of the sites. A storage layer of the clusters provides shared storage to the multiple VMs across the multiple sites. One of the sites is configured as an active storage site configured to receive and service I/O requests from the compute layer. A single instance of the application is active at a time and configured as a “compute owner” of the shared storage to issue the I/O requests to the shared storage. The compute owner and active storage site may not be co-located on the same site, leading to excessive I/O and PR activity patterns indicative of degraded performance. Upon detecting such patterns, the technique automatically triggers a storage failover to ensure that compute owner and active storage site are co-located at the same site.