Emc Corporation

Red Hat, Inc.

Brett D Niver

Steven T McClure

Steven R Chalmer

Gabriel Zvi BenHanokh

William F Baxter

Stephen D MacArthur

Yechiel Yochai

Ramprasad Shetty

Louis Krigovski

Man Min Moy

Mark J Halstead

Haim Kopylovitz

John K Walton

Kendell Alan Chilton

David Reese

Ofer Michael

Avinash Kallat

Joshua Durgin

Richard Wheeler

Yuval Lifshitz

Michael Bermingham

Robert DeCrescenzo

Mark David Nelson

James M McGillis

Kevin Granlund

Matthew William Benjamin

Adam Kupczyk

Casey Taylor Bodley

Qin Wang

David Zafman

Mohammad Faisal Siddiqui

David L Scheffey

Neha Ojha

Joshua Nikolai Durgin

Data requests can be serviced by multiple paths of smart network interface cards (NICs). For example, a system can receive a request for data at a first path of a smart NIC. The first path can be a hardware-implemented path. The system can send one or more parameters of the request to a second path of the smart NIC. The second path can be a slower path than the first path and configured to execute a routing algorithm for the request. The system can receive routing information for the request from the second path based on the routing algorithm and transmit the request to a storage node based on the routing information.

Data request servicing using multiple paths of smart network interface cards

Distributed storage nodes having specialized hardware can be pooled for servicing data requests. For example, a distributed storage system can include a group of storage nodes. The distributed storage system can determine a subset of storage nodes that include the specialized hardware based on status information received from the group of storage nodes. The specialized hardware can be preconfigured with specialized functionality. The distributed storage system can then generate a node pool that includes the subset of storage nodes with the specialized hardware. The node pool can be configured to perform the specialized functionality in relation to a data request.

Pooling distributed storage nodes that have specialized hardware

Power consumption can be reduced by selective memory chip hibernation. For example, a computing device can allocate first data associated with a first processing operation of a user device to a first chip of a dynamic random access memory (DRAM) of the user device. The computing device can allocate second data associated with a second processing operation of the user device to a second chip of the DRAM of the user device. The computing device can determine the first processing operation has been inactive for a predetermined period of time and migrate the first data from the first chip of the DRAM to a storage device of the user device. The computing device can hibernate the first chip of the DRAM while maintaining power to the second chip of the DRAM for continuing to perform the second processing operation.

Reducing power consumption by selective memory chip hibernation

A notification configuration associated with an object is received by a first host system from a client device. The notification configuration causes host systems to generate notifications for the client device upon storing the object at the host systems. The object is stored in a first memory of the first host system. The notification configuration is transmitted by the first host system to a second host system. The object is provided to the second host system, wherein the second host system is to transmit a notification to the client device upon storing the object at a second memory of the second host system.

Client driven multi-site consistency for object storage

Replicas of content can be managed in storage systems. In one example, a storage system can determine an amount of load on the storage system based on values for performance metrics indicating a performance of the storage system. Next, the storage system can determine that the storage system is to have a target number of replicas of content based on the amount of load on the storage system. The storage system can then adjust itself to have the target number of replicas of the content.

Managing replicas of content in storage systems

Methods and systems are disclosed for providing resource sharing in a computing environment using file descriptor isomorphism. The methods and systems may perform a method in a computing environment having processor systems executing processes. The method may include receiving a request from a first process to access a first resource. Further, the method may include generating a first Global File Descriptor (GFD) that references a first entry in a GFD table, the first GFD entry including a reference to a first entry in a resource descriptor table pointing to the first resource. Based on the request, at least one GFD field associated with the first GFD entry is configured. Thus, methods and systems may manage access by the first process to the first resource using the first GFD entry.

Methods and systems for providing resource sharing through file descriptor isomorphism

Described are techniques for preserving connections. First code is executed on a server. The server communicates with a client over one or more connections and the first code uses one or more control structures describing a state of the one or more connections. An operation is performed on the server. First processing is performed in response to the operation. The first processing includes loading second code for execution on the server. The second code replaces the first code and uses the one or more control structures previously used by the first code.

Techniques for persistence of connections

A system for error correction processing includes methods, software and/or devices for generating and using correction packets that may provide for the rebuilding of a lost data packet or other information packet. A correction packet may be generated at a transmitting device that corresponds to a plurality of packets transmitted to a destination device. The correction packet may be transmitted to the destination device separately from the transmitting of the plurality of packets. The correction packet may be received at the destination device, and a determination may be made as to whether at least one of the plurality of packets transmitted to the destination device is a lost packet that has not been received at the destination device. If the lost packet of the plurality of packets is determined, the lost packet may be rebuilt using the correction packet.

Side channel for forward error correction used with long-haul IP links

Described are techniques for determining a set of routing information for a plurality of components performing routing in a network. Destinations that are directly connected to each of the plurality of components are determined. Each of the plurality of components is associated with one of a plurality of routing tables. Each of the plurality of routing tables stores routing information in accordance with destinations in the network. Cost information is stored in the plurality of routing tables for each destination directly connected to one of the plurality of components. For each of the plurality of components, a set of neighboring components is determined. For each neighboring component, routing information for a destination is adopted from the routing table of said each neighboring component in accordance with an adoption rule. Processing is repeatedly performed until the routing tables have not been modified.

Techniques for fault tolerant routing in a destination-routed switch fabric

In a methods and systems of controlling a process's access to a device driver, a lock may be used to establish a process wait state or to wake up one or more processes. A spinlock may be used to acquire a lock associated with a device driver. The lock includes a lock value representing the availability of the lock. If the lock value is a first value, the process acquires the lock and sets the lock value to a second value. Otherwise, the process returns to the step of using the spinlock to acquire the lock associated with the device driver. If the lock is acquired, the process accesses the device driver. If the device is not ready, the process is set to wait for the lock. Waiting for the lock comprises setting a field of the process to a pointer to the lock and setting a state of the process to waiting. After the device has been successfully accessed or the process has been set to wait for the lock, the lock is released typically by setting the lock value to the first value.

Systems and methods for suspending and resuming threads

A data storage system having a packet switching network, a cache memory, and a plurality of directors, one portion of such directors being adapted for coupling to a host computer/server and another portion of the directors being adapted for coupling to a bank of disk drives. The plurality of directors and cache memory are interconnected through the packet switching network. Each one of the directors is adapted to transmit different types of information packets to another one of the directors through the network. Each one of the directors is adapted to transmit and receive different types of information packets to another one of the directors or cache memories through the packet switching network. Each one of the cache memories is adapted to receive and transmit different types of information packets to one of the directors through the packet switching network. One type of information packet requires a different degree of latency than another type of information packet. The system includes an arbiter for transmitting the information packets as a function of the latency requirement, a priority assigned to the information packet, and the age of such information packets having been stored in a queue of the transmitting one of the directors, the packet switching network, or one of the cache memories.

Data storage system having packet switching network with latency arbitration

Described is an end-to-end broadcast-based messaging technique used in controlling message flow in a data storage system. Each node stores flow control state information about all the nodes which is used in determining whether to send a data transmission to a receiving node. The flow control state information includes an indicator as to whether each node is receiving incoming data transmissions. If a node is not receiving incoming data transmissions, the flow control state information also includes an associated expiration time. Data transmissions are resumed to a receiving node based on the earlier of a sending node determining that the expiration time has lapsed, or receiving a control message from the receiving node explicitly turning on data transmissions. Each node maintains and updates its local copy of the flow control state information in accordance with control messages sent by each node to turn on and off data transmissions. Each node sends out control messages in accordance with predetermined threshold levels taking into account hardware and/or software resources for message buffering.

End-to-end broadcast based flow control in a switch fabric

A process scheduling method includes executing a plurality of symmetric schedulers on respective processors of a multiprocessing system. Each scheduler periodically accesses a shared lock to obtain exclusive access to a shared scheduling data structure including (a) process information identifying the processes, and (b) scheduling information reflecting the executability and priorities of the processes. After obtaining the lock, each scheduler performs a scheduling routine including (a) utilizing the scheduling information and a scheduling algorithm to identify a next executable process, and (b) (1) activating the identified process to begin executing on the processor on which the scheduler is executing, and (2) updating the scheduling information to reflect the activation of the identified process. The scheduler then accesses the lock to relinquish exclusive access to the scheduling data structure. The fully symmetric scheduler provides for efficient, high-performance scheduling especially in embedded multiprocessing computer systems in which the rate of process context switches may be several thousand per second.

Distributed task scheduling for symmetric multiprocessing environments

Methods and systems consistent with the present invention may facilitate error tracing in computer software. Such methods and systems may maintain context information of a target process, swap from a context of the target process to a context of an error-tracing process, and trace an error from the target process using the error-tracing process and the context information of the target process.

Systems and methods for tracing errors

A method for determining throughput of a data passing between end points of a data communication system as a function of bit error rate, comprising: generating a mathematical model of the functional relationship between the throughput of data passing from a transmitting one of a pair of end points of a data communication system and a receiving one of the pair of end points and a bit error rate of data received at the receiving one of the pair of end points.

Growing community of inventors

Waltham, MA, United States of America

Brett D Niver