International Business Machines Corporation

Pernixdata, Inc.

Vmware, Inc.

Michal Ostrowski

Orran Yaakov Krieger

William Joseph Armstrong

Randal Craig Swanberg

Satyam B Vaghani

Murali Vilayannur

Woon Ho Jung

Kaustubh Sambhaji Patil

Poojan Kumar

Paul Edward McKenney

Bradly George Frey

Andrew Henry Wottreng

Renato John Recio

Naresh Nayar

Charles Scott Graham

Xiaoxin Chen

Kyle Alan Lucke

Cathy May

Benjamin J Corrie

Richard McDougall

Wei Lun Huang

Sandy K Kao

Akhilesh Joshi

Mahesh Vinayak Patil

Shyan-Ming Perng

Bryan Jeffrey Crowe

Qicheng Christopher Li

Deepak Muley

Methods, systems, and computer programs for providing an application server appliance utilizing one or more virtual machines are described. The application server appliance may be a virtual machine having a reduced guest operating system, a runtime environment, and a management agent installed therein. An appliance controller automatically determines one or more configurations and/or settings for the runtime environment based on a variety of factors, including the set up of the virtual machine appliance. The appliance controller generates an application package having the determined settings and transmits the package to the application server appliance, wherein the application package is configured to be executed by the runtime environment.

Execution of an application in a runtime environment installed in a virtual appliance

Example distributed caching systems and methods are described. In one implementation, a system has multiple host systems, each of which includes a cache resource that is accessed by one or more consumers. A management server is coupled to the multiple host systems and presents available cache resources and resources associated with available host systems to a user. The management server receives a user selection of at least one available cache resource and at least one host system. The selected host system is then configured to share the selected cache resource.

Distributed caching systems and methods

A cache manager maintains coherency of cached objects used by applications in a computing system. The cache manager maintains a cache memory of objects as they are accessed by an application. The cache manager tracks cached objects on a per-application basis using a cache database, storing for each object metadata comprising the generation number of the application using the cached object, and the file generation number of the file from which the object was read. The cache manager determines whether cached objects are valid and can be used by the application, or are stale and must be reloaded, by using these generation numbers when an application attempts to use a file or object. In this fashion, cache coherency is maintained even in a distributed environment without the centralized cache management bottlenecks of prior approaches and without the need to eagerly purge the cache of stale versions of objects.

System and method for maintaining cache coherency

When a virtual machine sends a write command to a host operating system, a cache system stores the record included in the write command and later sends the write command to a storage system. Systems and methods store an indication of when the write command was received along with the received records in the cache. The cache system determines an order of the records from the indication. In some instances, records received at the same time are serialized and/or assigned record numbers. The simultaneously received records can be assigned a batch number. According to the determined order, the records are retrieved from the cache memory and included in write commands sent to the storage system. In some instances, checkpoints can be stored to prevent records from being re-sent to the storage system following a failure.

Systems and methods to manage write commands in a cache

Systems and methods for managing records stored in a storage cache are provided. A cache index is created and maintained to track where records are stored in buckets in the storage cache. The cache index maps the memory locations of the cached records to the buckets in the cache storage and can be quickly traversed by a metadata manager to determine whether a requested record can be retrieved from the cache storage. Bucket addresses stored in the cache index include a generation number of the bucket that is used to determine whether the cached record is stale. The generation number allows a bucket manager to evict buckets in the cache without having to update the bucket addresses stored in the cache index. Further, the cache index can be expanded to accommodate very small records, such as those generated by legacy systems.

Systems and methods to manage cache data storage

A method in a data processing system is provided for processing a service request of a client partition. The method includes: obtaining by a service partition of the data processing system the service request from the client partition, wherein both the client and service partitions execute above a hypervisor of the data processing system; and processing the service request by the service partition utilizing a processor quantum assigned to the client partition and donated by the client partition to the service partition. The client partition controls scheduling of the service partition by queuing the service request at the client partition until the client partition decides to proceed with execution of the service request by the service partition. In one implementation, the service partition is a partition adjunct of the data processing system, which utilizes donated virtual address space of the client partition.

Client partition scheduling and prioritization of service partition work

Multiple logical partitions are provided access to a self-virtualizing input/output device of a data processing system via multiple dedicated partition adjunct instances. Access is established by: interfacing each logical partition to one or more associated partition adjunct instances, each partition adjunct instance coupling its associated logical partition to one of a virtual function or a queue pair of the self-virtualizing input/output device, and each partition adjunct instance being a separate dispatchable state and being created employing virtual address space donated from the respective logical partition or a hypervisor of the data processing system, and each partition adjunct instance including a device driver for the virtual function or queue pair of the self-virtualizing input/output device; and providing each logical partition with at least one virtual input/output which is interfaced through the logical partition's respective partition adjunct instance(s) to a virtual function or queue pair of the self-virtualizing input/output device.

Multiple partition adjunct instances interfacing multiple logical partitions to a self-virtualizing input/output device

An approach is provided in a hypervised computer system where a page table request is at an operating system running in the hypervised computer system. The operating system determines whether the page table request requires the hypervisor to process. If the determination reveals that the page table request requires the hypervisor, then the hypervisor is used to handle the request. However, if the determination reveals that the page table request does not require the hypervisor, then an indicator included in a page table entry corresponding to the request is read to determine if the page table entry is controlled by the operating system or the hypervisor. The operating system is able to update the page table entry if the indicator identifies the page table entry as being operating system controlled.

Operating system management of address-translation-related data structures and hardware lookasides

A computer system having a plurality of processor cores utilizes a device driver running in a driver virtual machine to handle I/O with the corresponding device for other virtual machines. A hypervisor in the computer system receives an interrupt from the corresponding device and identifies a virtual machine that best correlates to the received interrupt prior to forwarding the interrupt for handling by the driver virtual machine. The hypervisor then speculatively transmits a notification to the identified virtual machine to wake up and poll a memory shared between the identified virtual machine and the driver virtual machine. Once the driver virtual machine completes handling of the forwarded interrupt, it copies data made available by the corresponding device to the shared memory for access by the polling identified virtual machine.

Providing notification to speculatively waking up target virtual machine for an I/O event using multiple virtual machines and processors

A partition adjunct is provided for a logical partition running above a hypervisor of a data processing system. The partition adjunct, which is a separate dispatchable partition from an instantiating logical partition, provides one or more services to the logical partition. A service request received from the logical partition is processed by the partition adjunct utilizing virtual address space donated to the partition adjunct from the logical partition. The partition adjunct and the logical partition share a common virtual address to real address page table, and context switching the current state machine from the logical partition to the partition adjunct occurs without invalidating or modifying state data of selected memory management and address translation hardware of the data processing system. In a hardware multithreaded system, the partition adjunct is dispatched on a single thread, while another thread continues to run in the logical partition initiating the service request.

Partition adjunct for data processing system

Dedicated access is provided to a physical input/output (I/O) device which is non-configurable by an initiating logical partition. Access is established by: initiating, by the logical partition, creation of a partition adjunct; invoking a hypervisor of the data processing system to instantiate the partition adjunct with resources donated from the initiating logical partition, the donated resources including a donated virtual address space of the logical partition and the physical I/O device; creating, by the hypervisor, the partition adjunct and assigning the donated virtual address space and donated physical I/O device to the created partition adjunct; and interfacing, by the hypervisor, the logical partition and the created partition adjunct, the interfacing including providing the logical partition with a virtual I/O device which replaces the donated physical I/O device, and which is configurable by the logical partition.

Partition adjunct with non-native device driver for facilitating access to a physical input/output device

Access control to shared virtual address space within a single logical partition is provided. The access control includes: associating, by a hypervisor of the data processing system, a memory protection key with a portion of a single logical partition's virtual address space being shared by multiple entities, the key preventing access by one of the multiple entities to that portion of the virtual address space, and allowing access by another of the entities to that portion of the virtual address space; and locking by the hypervisor the memory protection key from modification by the one entity, wherein the locking prevents the one entity from modifying the key and thereby gaining access to the portion of the single logical partition's virtual address space with the associated memory protection key. In one embodiment, the one entity is the single logical partition itself, and the another entity is a partition adjunct.

Growing community of inventors

Austin, TX, United States of America

Michal Ostrowski