International Business Machines Corporation

Sanket Rathi

Kiran Kumar Anumalasetty

Sudhir Maddali

Venkata N S Anumula

Yadagiri Rajaboina

Vinod Kumar Boddukuri

James P Allen

Rajaboina Yadagiri

Harikrishna K Manchineni

Purna Chandra Jasti

Nicholas S Ham

Prashant Sreedharan

Bruce Gerard Mealey

Madhusudanan Kandasamy

Pruthvi Panyam Nataraj

Mallesh K Lepakshaiah

Sangeeth Keeriyadath

Vamshikrishna Thatikonda

Ramana R Machireddy

Abhishek Mishra

Manish Sharma

Bhyrav M Mutnury

James Anthony Pafumi

Phani Kumar V U Ayyagari

Stephen M Tee

Gary Steven Domrow

Venkata N Anumula

Phani K Ayyagari

Purna Chandra R Jasti

Venkata Naga Seshaiah Anumula

Ramesh Kumar Marupaka

Venkata Ns Anumula

Populating cache of a virtual server. A data record is generated that is associated with a first virtual server. A set of data is saved that describes data in a cache that is associated with the first virtual server. In response to either (i) a failover of the first virtual server or (ii) a migration request for the first virtual server, a cache of a second virtual server is populated based on the set of data.

Leveraging server side cache in failover scenario

Embodiments include systems, methods, and computer program products to perform an operation for enabling multipath I/O for logical volume backed virtual disks through redundant virtual I/O servers (VIOSs) on a computing system. The operation generally includes creating, from a physical storage device, a logical volume on a first VIOS. The logical volume on the first VIOS is activated in a first access mode. The operation also includes importing the logical volume to a second VIOS. The logical volume on the second VIOS is activated in a second access mode different from the first access mode. The operation further includes mapping the logical volume on the first and second VIOSs as a backing storage device for at least one logical partition hosted on the computing system.

Supporting MPIO for logical volume backed virtual disks

Embodiments describe an approach for improving path selection in multi-virtual input/output sever environment. Embodiments, send one or more inquiry commands to one or more virtual input/output server's (VIOSs). Further, embodiments, receive one or more server-side cache properties from the one or more VIOSs. Additionally, embodiments, determine one or more preferred paths based on the one or more server-side cache properties, and perform one or more input/output's (I/O's) on the one or more preferred paths.

Server-side path selection in multi virtual server environment

I/O recovery for storage side cable movement in fabric-assigned WWPN fabrics including receiving a state change notification indicating a change to a first fabric-assigned world-wide port name (WWPN) on a fibre channel switch; pausing I/O activity for active logical unit numbers (LUNs) connected to the fibre channel switch via the first fabric-assigned WWPN; obtaining a list of potential fabric-assigned WWPNs; requesting, via the fibre channel switch, a reported list of LUNs from each fabric-assigned WWPN in the list of potential fabric-assigned WWPNs; comparing each reported list of LUNs to the paused active LUNs to determine a second fabric-assigned WWPN from the list of potential fabric-assigned WWPNs to which the paused active LUNs are connected; updating, with the second fabric-assigned WWPN, connection information for the paused active LUNs; and resuming I/O activity for the paused active LUNs using the updated connection information.

I/O recovery for storage side cable movement in fabric-assigned world-wide port name fabrics

An interface superpipe is implemented in a filesystem. A filesystem in a kernel, receives a command to open a file, the command issued in the execution of a process in an application. The file is determined to be on an interface disk. It is determined that a context does not exist for the process and, in response, an adapter queue is allocated for the process in a kernel memory and mapped into a process address space associated with the process. The context information of the process is saved in the kernel memory. The filesystem may be part of a system further comprising a processor, a storage, an interface adapter in communication with the storage and sharing a memory space with the processor, and an application in communication with the filesystem.

Transparent CAPI exploitation for legacy application

Improved techniques for memory expansion are provided. A storage volume is opened on a storage device attached to a computing system, and the storage volume is configured as extended memory. A number of hardware threads available in the computing system are determined, and a number of contexts equal to the determined number of hardware threads are generated. Each context is assigned to one of the hardware threads. It is further determined that a first hardware thread has requested a first page that has been paged to the storage volume, where the first hardware thread is assigned a first context. A synchronous input output (I/O) interface is accessed to request that the first page be moved to memory, based on the first context. While the first page is being moved to memory, a priority of the first hardware thread is reduced.

Use of capi-attached storage as extended memory

A system and method for transferring a logical partition is provided that includes (i) a source server having a logical partition and at least one virtualized port for communication with at least one physical access port; (ii) a target server having at least one physical access port; and (iii) a storage server having a plurality of access ports, where a first access port is configurable to be in communication with the source server and a second, different access port is configurable to be in communication with the target server, wherein the logical partition has a first I/O path that includes the first access port of the storage server, and wherein the system and method is configurable to create a second I/O path for the logical partition that includes the second access port of the storage server.

Live partition migration of virtual machines across storage ports

An approach for avoiding overloads of network adapters. The approach receives one or more requests from one or more virtual machines, wherein the one or more requests are directed to one or more network adapters. The approach determines whether a first network adapter of the one or more network adapters is saturated. Responsive to a determination that the first network adapter is saturated, the approach sends a first busy event to a first virtual machine of the one or more virtual machines.

Avoiding overloading of network adapters in virtual environments

Methods and apparatuses for protecting data integrity in a multiple path input/output environment are provided. When sending a write command that includes data to be written to a target device from an initiator device over a specified first path of a plurality of paths by which the target device is in communication with the initiator device when a fault in the first path is detected and the status of the write command indicates that the write command was fully transmitted to the target device, a second path of a plurality of paths is selected, a reset command is sent over the second path from the initiator device to the target device, and after sending the reset command, the data are retransmitted in a second write command that a path other than the first path from the initiator device to the target device.

Protecting data integrity in a multiple path input/output environment

An approach to virtualizing a coherent memory hardware accelerator is provided comprising creating a segment table for a client logical partition (LPAR), wherein a virtual address space is reserved in the segment table, receiving an Input/Output (I/O) request to use the coherent memory hardware accelerator, generating an I/O operation associated with the I/O request, wherein the I/O operation is passed to the coherent memory hardware accelerator, receiving a map request from the coherent memory hardware accelerator, creating an entry in the reserved virtual address space in the segment table, creating a hardware page table map request for mapping a memory address associated with the client LPAR and returning the reserved virtual address space to the coherent memory hardware accelerator, wherein the coherent memory hardware accelerator has remote direct memory access to memory associated with the client LPAR for performing an acceleration of one or more processes.

Virtualizing coherent hardware accelerators

Dynamic reconfiguration of queue pairs in a data processing system is provided. A device driver determines whether a dynamic CPU reconfiguration has added one or more CPUs to the data processing system, wherein the data processing system comprises a number of CPUs and a number of queue pairs. Responsive to the dynamic CPU configuration adding one or more CPUs, the device driver allocates a portion of a memory corresponding to a queue pair, wherein each queue pair comprises a receive queue and a transmit queue, programs a receive side scaling mechanism in a network adapter to allow for dynamic insertion of a processing engine associated with the queue pair, and enables transmit tuple hashing to the queue pair.

Dynamic reconfiguration of queue pairs

According to one exemplary embodiment, a method for VIOS failover in an environment with a physical storage adapter is provided. The method may include assigning the physical storage adapter to a first VIOS, wherein the physical storage adapter has I/O connectivity to at least one storage device. The method may include configuring a first I/O path between the first VIOS and a second VIOS. The method may include configuring a second I/O path from a client partition to the first VIOS, wherein the second I/O path is set as a primary I/O path. The method may include configuring a third I/O path from the client partition to the second VIOS. The method may include determining the first VIOS is inaccessible. The method may include unassigning the physical storage adapter from the first VIOS. The method may include assigning the physical storage adapter to the second VIOS.

Growing community of inventors

Hyderabad Telangana, India

Sanket Rathi