International Business Machines Corporation

Nutanix, Inc.

Globalfoundries Inc.

Manoj Premanand Naik

Frank Bernhard Schmuck

Dean Hildebrand

Renu Tewari

Marc M Eshel

Roger Lee Haskin

Kalpesh Ashok Bafna

Wayne A Sawdon

Durga Mahesh Arikatla

Deepavali M Bhagwat

Rajagopol Ananthanarayanan

Hemanth Kumar Thummala

Saji Kumar Vijaya Kumari Rajendran Nair

Riyazahamad Moulasab Shiraguppi

Kalyan Chakravarthy Gunda

Shyamsunder Prayagchand Rathi

Manish Satyapal Gupta

Karan Gupta

Anil Kumar Gopalapura Venkatesh

Eric Wang

Mausumi Ranasingh

Yifeng Huang

Sanath Kumar Kalligundi Shivaswamy

Veerraju Tammineedi

Manosiz Bhattacharyya

Shankar Balasubramanian

Venkateswara Rao Puvvada

Rajagopal Ananthanarayanan

Ravindra Sure

Uday Kiran Jonnala

Pradeep Thomas

Mansi Ajit Shah

Kavitha Pasikanti

Gaurav Kumar

Lakshmana Reddy

Dheer Moghe

Anurag Sharma

Juan C Gomez

Rashmi Gupta

Pankaj Kumar Sinha

Sagar Gupta

Ketan Kotwal

Gaurav Gangalwar

Hemantha Kumar Thummala

Srikrishan Malik

Sravan Kumar Muthyala

Sanika Nitin Mokashi

Deepak Tripathi

Sukruth Sridharan

Daniel Chilton

Will Strickland

Atul Kumar

Andrey Khilko

Ashok Tellakula

Mansi A Shah

Examples of systems described herein may manage durable handles for seamless failover. Durable handles may be stored in a persistent volume group. The persistent volume group may be moved, together with all or a portion of file share data, to another computing node responsive to an indication of a failure event. To accommodate asynchronous write shares, asynchronous write operations may also be provided to the target computing node. The asynchronous write operations may be processed before reconnecting clients to the file share.

Durable handle management for failover in distributed file servers

A replication policy management and scheduling technique of a Files service is configured for deployment in multi-site data replication environments. The technique involves policy management for data distribution and/or data consolidation (concentration) where multiple sources, e.g., file system (FS) clusters or sites, replicate the data to a central target FS site, e.g., in a spoke and hub arrangement typical of remote office/branch office environments. The technique also involves creation and configuration of a main replication policy by a customer at a central resource manager configured to interact and manage the FS sites, each of which includes one or more file server virtual machines.

Replication policy management and scheduling technique of a files service

A unified namespace technique provides coherent access to unstructured data across different data access protocols having different logical constructs that are stored and managed on a storage system. A control plane infrastructure operates in connection with storage services to provide support for a vast array of storage platforms including file servers of a file system and object storage servers of an object store. Metadata associated with a data access transaction is processed separately and natively by a protocol stack of a particular storage service according to a particular data access protocol. The processed metadata is stored native to the access protocol in a metadata store associated with the particular storage service and is made available to the protocol stacks of the other storage services. Processed metadata is made available to the protocol stacks via an event notification logging service implemented as a message bus. A single canonical instance of the data is maintained for all of the logical constructs served by the storage system.

Unified namespace across data access protocols

Examples of systems described herein include a file server virtual machine of a virtualized file server configured to manage storage of a plurality of storage items. The file server virtual machine including a file system configured to receive an access request directed to a storage item of the plurality of storage items and associated with a user. The file system is further configured to retrieve an access control list having permissions information associated with the storage item, and to cache a permissions profile for the user including all permissions pertaining to the user for the storage item. The file system is further configured to determine whether the access request is permissible based on the cached permissions profile.

Handling permissions for virtualized file servers

An elastic request handling technique limits a number of threads used to service input/output (I/O) requests of a low-latency I/O workload received by a file system server executing on a cluster having a plurality of nodes deployed in a virtualization environment. The limited number of threads (server threads) is constantly maintained as 'active' and running on virtual central processing units (vCPUs) of a node. The file system server spawns and organizes the active server threads as one or more pools of threads. The server prioritizes the low-latency I/O requests by loading them onto the active threads and allowing the requests to run on those active threads to completion, thereby obviating overhead associated with lock contention and vCPU migration after a context switch (i.e., to avoid rescheduling a thread on a different vCPU after execution of the thread was suspended).

Elastic request handling technique for optimizing workload performance

Examples of a virtualized file server that persistently stores file system event data records are described. The virtualized file server may include an audit framework with a connector publisher that is configured to publish the event data records and other information for consumption by other services using a message system. The event data records may include data related to various operations on the file system executed by the VFS. The VFS may persistently store event data records according to a data retention policy and/or until an event data record is consumed by one or more particular services.

Virtualized file servers and methods to persistently store file system event data

An example file server manager updates a selected share of a destination distributed file server based on a snapshot of at least a portion of a selected share of a source distributed file server. The selected share of the destination distributed file server is updated while the source distributed file server serves client requests for storage items of the selected share of the source distributed file server. The file server manager receives a request to failover from the source distributed file server to the destination distributed file server and configures the destination distributed file server to service read and write requests for storage items of the selected share of the destination distributed file server. The file server manager further redirects client requests for storage items of the selected share of the source distributed file server to the destination distributed file server by updating active directory information.

Failover and failback of distributed file servers

Examples described herein are generally directed towards file server access controls, and more specifically towards a mechanism to create consistent access control lists for local users across different file servers in a distributed file server environment. In operation, a local user system SID (e.g., external SID) may be generated for a first user of a first file server. A global ID based on attributes associated with the user of the first file server may also be generated. The global ID for the user may be stored in metadata associated with an access control list (ACL) for a file accessible through the first file server. Data, including the file may be migrated to a second file server. Based on receiving an access request at the second file server associated with the user based on the external ID, the external ID for the user may be translated into the global ID, and used to determine access to the file.

Consistent access control lists across file servers for local users in a distributed file server environment

This disclosure relates to scope-based lock management for shared resources of a distributed computing system. A scope-based lock manager may grant a request for a lock of a shared resource of the distributed computing system, where the lock request includes a scope of the lock and a target having the scope. The target may define entities able to access the shared resource when locked. The scope and target of the lock are stored at a lock database including scopes and targets associated with additional locks of additional shared resources of the distributed computing system. The scope based lock manager may determine when a computing node of the distributed computing system has failed and remove the lock from the lock database responsive to a determination that the target of the lock is hosted on the computing node.

Scope-based distributed lock infrastructure for virtualized file server

An example file server manager disclosed herein receives a registration for a distributed file server, where the distributed file server is hosted in a virtualization environment and includes a cluster of file server virtual machines configured to provide access to a file system. The file server manager further synchronizes metadata with the distributed file server, the metadata including identification of each of the file server virtual machines of the cluster of file server virtual machines, the metadata including information regarding the file system and receiving a management request for the distributed file server. The file server manager further formats the management request for the virtualization environment based on the metadata and utilizing information from the registration to access the distributed file server with the formatted management request.

File server managers and systems for managing virtualized file servers

A file server manager disclosed herein accesses information regarding a selected share of a source distributed file server for replication, where the selected share stores at least a portion of a namespace of storage items and is hosted by a first file server virtual machine of the source distributed file server. The file server manager accesses a mapping between virtual machines of the source distributed file server and virtual machines of the destination distributed file server and replicates the selected share to a second file server virtual machine of the destination distributed file server based on the mapping. The file server manager directs a request to read a first storage item to the destination distributed file server and directs a request to write to a second storage item to the source distributed file server while the destination distributed file server services the request to read the first storage item.

Share-based file server replication for disaster recovery

Examples described herein include virtualized environments including a virtualized file server. Examples of file server virtual machine managers are described which may setup and/or configure file server virtual machines in accordance with a target number of connections and/or a target throughput for the virtualized file server. The virtualized file server may be scaled up, scaled down, scaled in, and/or scaled out.

Virtualized server systems and methods including scaling of file system virtual machines

Examples of systems described herein include a virtualized file server including a first file server virtual machine and a second file server virtual machine configured to manage a distributed file share of storage items. The second file server virtual machine is configured to manage a particular storage item of the distributed file share of storage items. The first file server virtual machine is configured to, in response to receipt of a referral request for a file share path for the particular storage item from a client, look up a file share path for the particular storage item in a map of at least a portion of the distributed file share of storage items, and provide a referral with the file share path that identifies the second file server virtual machine.

Transparent referrals for distributed file servers

Growing community of inventors

San Jose, CA, United States of America

Manoj Premanand Naik