Sun Microsystems, Inc.

Oracle America, Inc.

Violin Memory Inc.

Terraspring, Inc.

Gear Six, Inc.

Martin Patterson

Ashar Aziz

Thomas Markson

Christopher Mark Eppstein

Glenn Carter Scott

Geoffrey G Baehr

Geoffrey Mulligan

Nisha D Talagala

Tom R Markson

Thomas L Lyon

Mark Gray

Carolyn Turbyfill

William Danielson

David S Allison

Pavani Naishadh Diwanji

Shriram Krishnan

Benjamin H Stoltz

Michael R Sheridan

Steven Peart

Jayaraman Manni

Osman Abdoul Ismael

James Samuel Bowen

Matthias Oberdorfer

Christopher T La

Berry Kercheval

Christopher J Conway

Edward Pernicka

Patrick A Tickle

Qing Huang

Rama Chitta

Tom Markson

A method and apparatus of providing high performance and highly scalable storage acceleration includes a cluster node-spanning RAM disk (CRD) interposed in the data path between a storage server and a computer server. The CRD addresses performance problems with applications that need to access large amounts of data and are negatively impacted by the latency of classic disk-based storage systems. It solves this problem by placing the data the application needs into a large (with respect to the server's main memory) RAM-based cache where it can be accessed with extremely low latency, hence improving the performance of the application significantly. The CRD is implemented using a novel architecture which has very significant cost and performance advantages over existing or alternative solutions.

Method and apparatus for providing high-performance and highly-scalable storage acceleration

A multi-tiered cache manager and methods for managing multi-tiered cache are described. Multi-tiered cache manager causes cached data to be initially stored in the RAM elements and selects portions of the cached data stored in the RAM elements to be moved to the flash elements. Each flash element is organized as a plurality of write blocks having a block size and wherein a predefined maximum number of writes is permitted to each write block. The portions of the cached data may be selected based on a maximum write rate calculated from the maximum number of writes allowed for the flash device and a specified lifetime of the cache system.

Efficient use of hybrid media in cache architectures

An approach for allocating resources to an apparatus generally involves a resource allocator receiving a request that specifies one or more characteristics for the apparatus. A resource allocator determines the logical devices to be included in the apparatus so that the apparatus has the specified characteristics. For at least one logical device, the resource allocator determines whether a physical device is available that corresponds to the logical device. If a physical device is available, the resource allocator allocates the physical device to the apparatus. If a physical device is not available, the resource allocator does not allocate the physical device to the apparatus.

Approach for allocating resources to an apparatus

An approach for allocating resources to an apparatus based on suspendable resource requirements generally involves a resource allocator determining that a particular resource requirement for an apparatus is to no longer be satisfied, such as for a suspendable resource requirement. The resource allocator de-allocates the one or more resources that satisfy the particular resource requirement from the apparatus. The resource allocator obtains and stores state information for a de-allocated resource so that another resource, which may or may not be the same as the resource that was de-allocated, can be allocated to the apparatus based on the stored state information with an acceptable loss of state.

Approach for allocating resources to an apparatus based on suspendable resource requirements

An approach for allocating resources to an apparatus based on resource requirements generally involves a resource allocator receiving a request that specifies resource requirements for the apparatus. A resource allocator determines whether resources are available that satisfy the resource requirements. If resources are available that satisfy a resource requirement, the resource allocator indicates that the resource requirement is fulfilled and the resources are allocated to the apparatus. If resources are not available that satisfy a resource requirement, the resource allocator indicates that the resource requirement is not fulfilled and the resources are not allocated to the apparatus. The apparatus is implemented based on the allocated resources.

Approach for allocating resources to an apparatus based on resource requirements

An approach for allocating resources to an apparatus based on alternative resource requirements generally involves a resource allocator determining that a resource that satisfies a resource requirement is not available, and based on the resource not being available, the resource allocator determines that another resource that satisfies another resource requirement is available. The resource allocator allocates the other resource to the apparatus, thereby allowing the apparatus to be implemented based on the other resource. The resource requirements are alternatives so that if the one alternative resource requirement cannot be fulfilled, the other alternative resource requirement can be fulfilled. Some alternatives can be preferred over other alternatives in a set of alternative resource requirements. In general, in a set of 'n' alternative resource requirements, 'm' resource requirements can be specified to be fulfilled, where &#x201c;m&#x201d; is less than &#x201c;n&#x201d; and &#x201c;n&#x201d; is two or greater.

Approach for allocating resources to an apparatus based on alternative resource requirements

A method for efficient communications with a cluster-based architecture preserves various aspects of integrity throughout one or more connections with a client, even in the midst of connection migration between nodes in the cluster. According to one aspect, the invention provides a mechanism for preventing the loss of packets arising from a TCP connection migration within the cluster. According to another aspect, the invention provides a mechanism for uniquely identifying conflicting TCP connections migrated to a common node. According to a still further aspect, the invention provides a distributed TCP timestamp mechanism so that the sender and receiver will have a consistent view of the timestamp even when each node has different local clock values and regardless of how many times the socket has been migrated.

Method and apparatus for efficient TCP connection handoff

An approach for allocating resources to an apparatus based on preemptable resource requirements generally involves a resource allocator determining that a resource that satisfies a resource requirement for one apparatus is not available but that another resource that currently satisfies another resource requirement for another apparatus does satisfy the resource requirement. The resource allocator determines that the other resource requirement for the other apparatus is characterized in that resources that currently satisfy the other resource requirement may be de-allocated from the other apparatus, such as a preemptable resource requirement. The resource allocator de-allocates the resource from the other apparatus and allocates the resource to the one apparatus. A preemptable resource requirement can be based on a suspendable resource requirement or a set of alternative resource requirements.

Approach for allocating resources to an apparatus based on preemptable resource requirements

An approach for provisioning network devices generally involves supplying boot data to network devices over a network so that the network devices can be booted up in an imaging mode or an application mode, depending upon the particular boot data supplied to the network device. When booted up in the imaging mode, imaging data can be downloaded and stored on network devices. When booted up in the application mode, the network devices execute one or more programs contained in the image data stored on the network devices. The first and second boot data may be in the form of boot loader scripts. Furthermore, the first and second boot data may be provided to the network device in the payload of a dynamic host configuration protocol (DHCP) reply. The DHCP reply may be generated and provided by a DHCP server to the network device in response to receiving a DHCP request from the network device. The approach may be implemented using a secure network environment.

Approach for provisioning network devices

The present invention relates generally to a method for efficient I/O handling in a cluster-based architecture. According to one aspect, the invention enables efficient scheduling of TCP connection migrations within a cluster. According to another aspect, the invention enables I/Os performed as TCP handoff operations to coexist on the same TCP/IP connection with I/Os performed as remote operations.

Method for efficient delivery of clustered data via adaptive TCP connection migration

Methods and apparatus providing a dynamically sized, highly scalable and available server farm are disclosed. A Virtual Server Farm (VSF) is created out of a wide scale computing fabric ('Computing Grid') which is physically constructed once and then logically divided up into VSFs for various organizations on demand. Each organization retains independent administrative control of a VSF. A VSF is dynamically firewalled within the Computing Grid. Allocation and control of the elements and topology in the VSF is performed by a Control Plane connected to all computing, networking, and storage elements in the computing grid through special control ports. No physical rewiring is necessary in order to construct VSFs in many different configurations, including single-tier Web server or multi-tier Web-server, application server, database server configurations.

Extensible computing system

An approach for allocating resources to an apparatus based on resource requirements generally involves a resource allocator receiving a request that specifies resource requirements for the apparatus. A resource allocator determines whether resources are available that satisfy the resource requirements. If resources are available that satisfy a resource requirement, the resource allocator indicates that the resource requirement is fulfilled and the resources are allocated to the apparatus. If resources are not available that satisfy a resource requirement, the resource allocator indicates that the resource requirement is not fulfilled and the resources are not allocated to the apparatus. The apparatus is implemented based on the allocated resources. A resource requirement can be optional so that if the optional resource requirement is not fulfilled, the apparatus can still be implemented. Conversely, a resource requirement can be necessary so that if the necessary resource requirement is not fulfilled, the apparatus is not implemented.

Approach for allocating resources to an apparatus based on optional resource requirements

A novel approach for determining an amount to be billed to a customer for the use of resources is based upon usage data and value data. The usage data indicates usage, by the customer, of a set of one or more resources during a specified period of time. The set of one or more resources may be dynamically selected and de-selected from a plurality of resources at any time. For example, the set of one or more resources may comprise a VSF as described herein. The value data indicates generally value provided by each resource from the set of one or more resources used during the specified period of time. The value provided by each resource may be expressed in service units per unit time and a charge may be applied for each service unit consumed during a specified period of time. Example billing schemes to which the approach is applicable include, without limitation, basic billing, flex billing, event flex billing and open flex billing.

Approach for determining an amount to bill a customer for the use of resources

A method and apparatus for replicating an image from a source to a destination disk are provided. Specific embodiments may be optimized for single source to multiple destination replication requests, for example. In one embodiment, the present invention provides tools and techniques for synchronous data replication responsive to asynchronous same-source-to-different-destination replication requests.

Tool for disk image replication

Methods and apparatus providing, controlling and managing a dynamically sized, highly scalable and available server farm are disclosed. A Virtual Server Farm (VSF) is created out of a wide scale computing fabric ('Computing Grid') which is physically constructed once and then logically divided up into VSFs for various organizations on demand. Each organization retains independent administrative control of a VSF. A VSF is dynamically firewalled within the Computing Grid. Allocation and control of the elements in the VSF is performed by a control plane connected to all computing, networking, and storage elements in the computing grid through special control ports. The internal topology of each VSF is under control of the control plane. A request queue architecture is also provided for processing work requests that allows selected requests to be blocked until required human intervention is satisfied.

Growing community of inventors

Menlo Park, CA, United States of America

Martin Patterson