Emc Corporation

Douglas Sullivan

Steven D Sardella

Stephen Edward Strickland

Alex J Sanville

Phillip H Leef

Robert P Valentine

Navin Sharma

Jun Ohama

David French

Peter John McCann

Robert W Beauchamp

John Kemeny

Michael John Kozel

Robert M Beauchamp

Brandon Barney

H Austin Spang, Iv

Matthew Yellen

Keith A Morrissette

Matthew Ferson

Phillip J Manning

Bill Buckley

Matt Yellen

Howard G Drake

William Buckley

Method for caching data

A data storage system includes a first storage processor including a first memory device; a second storage processor including a second memory device; and a third memory device coupled to the first storage processor and the second storage processor. The first and second storage processors are interconnected to enable mirroring of data between the first memory device and the second memory device. During a first mode of operation, data processed by the first storage processor and the second storage processor is mirrored between the first memory device and the second memory device and, during a second mode of operation, data processed by the first storage processor is mirrored from the first memory device to the third memory device.

System for caching data

A diplex FPGA is utilized to fan out a single high speed host universal asynchronous receiver transmitter ('UART') channel into a number of diplex UART channels. The diplex FPGA includes a microprocessor, memory, a host UART and a number of diplex UARTs. In operation, the microprocessor polls each of the UARTs in a 'round robin' manner and accepts packets from the host UART for transmission downstream and from the diplex UARTs for transmission upstream.

Method and system for facilitating communication between a host and downstream devices in a data storage system

A cooling system includes at least three fan units. A control unit operates each one of the at least three fan units, The control unit (a) operates only a selected two of the fan units, one of the at least three fan units being unselected and being inhibited from operation; (b) monitors operation of said selected two of fan units for a failure; and (c) upon detection of a failure in one of said selected two fan units, inhibits operation of the failed one of fan units and operating the unselected one of the at least three fan units.

Cooling system

Flow control settings are configured. Credit settings for credit types of input/output interconnect ports are programmed at a low value. The system type of a system containing the input/output interconnect ports is detected. The credit settings are reprogrammed in accordance with the system type.

Configuring flow control settings

A method and apparatus are provided for assigning/obtaining enclosure identification numbers in a distributed switch storage system. The method takes advantage a network topology wherein one port on the switch is always used as a downstream connection (towards a control station) and one always used as an upstream connection (away from the control station). Using single-hop type packets an assignment arbitration protocol ensures that each enclosure is assigned a unique and predictable Enclosure ID.

Server identification assignment in a distributed switched storage environment

A data storage system includes storage array and a switch that is configurable to create numerous network topologies within the system and to maintain separate communications paths between different computerized devices or networks and the storage array. For example, a user device and a service device, such as a system diagnosis device, can connect to the storage array through the switch. In order to isolate interaction or communication between the user and service devices, the switch can be logically partitioned into two distinct switches to form two distinct, isolated communications paths between the devices and the storage array. With isolated communications pathways established in the switch, in use, the service device is unable to access the user device coupled to the storage array.

Method and apparatus for providing a logical separation of a customer device and a service device connected to a data storage system

A technique controls a network switch having a set of ports. The technique involves configuring the network switch to provide an initial set of communications paths between the ports. The initial set of communications paths defines an initial communications path topology within the network switch. The technique further involves receiving a configuration command which identifies a particular operating mode of the data storage system after configuring the network switch to provide the initial set of communications paths within the network switch. The technique further involves reconfiguring the network switch to provide a new set of communications paths between the ports in response to the configuration command. The new set of communications paths (i) defines a new communications path topology within the network switch, the new communications path topology being different than the initial communications path topology, and (ii) supports the particular operating mode of the data storage system.

Techniques for controlling a network switch of a data storage system

A technique responds to a storage processor failure. The technique involves performing write-back caching operations using a cache of a first storage processor, and mirroring data from the cache of the first storage processor to a cache of a second storage processor. The technique further involves, after of a failure of the second storage processor in which the second storage processor becomes unavailable, continuing to perform write-back caching operations using the cache of the first storage processor while the second storage processor remains unavailable. A cache controller is capable of being modified so that any write data in the cache of the first storage processor persists if the first storage processor encounters a failure thus preventing loss of the cached write data.

Responding to a storage processor failure with continued write caching

A computerized system includes two storage processors having respective local write caches configured to mirror each other. When a first storage processor becomes unavailable and mirroring of the local write caches is prevented, the computerized system continues to attend to write operations from an external host in a write-back manner by caching write data from the write operations in the local write cache of the second storage processor. In response to a failure of the second storage processor, the computerized system preserves the write data within the local write cache of the second storage processor. Then, upon recovery of the second storage processor from the failure, the computerized system continues to attend to further write operations from the external host in the write-back manner by caching additional write data in the local write cache of the second storage processor while the first storage processor remains unavailable.

Recovering from a storage processor failure using write cache preservation

An I/O interface module of a storage system controller includes a management controller and power regulation and monitoring/control circuitry responsible for management of the I/O expansion module and pluggable I/O interface modules, which each include electrical power regulating circuitry to power circuit components. Temperature regulation components (e.g. fan and temperature sensor) provide a cooling airflow and monitor operating temperature. A controller works with the power regulation and monitor/control circuitry and temperature regulation components to perform first and second management activities concurrently. The first management activity involves managing the environmental operating conditions of the I/O expansion module itself, including (i) monitoring and regulating operating temperature and (ii) monitoring and controlling electrical power regulating circuitry of the power regulation and monitor/control circuitry. The second management activity involves managing environmental operating conditions of the I/O interface module, including (i) monitoring insertion and removal of the I/O interface module and reporting such insertion and removal to a separate controller within the storage system controller, (ii) controlling reset status of the I/O expansion module, and (iii) monitoring and controlling the electrical power regulating circuitry of the I/O interface module.

Storage system assembly with distributed enclosure management

Described is an enclosure that is configurable to perform either in-band or out-of-band enclosure management. The enclosure includes a midplane, a processor blade, and a management module. The processor blade has program code for collecting management information from other components in the enclosure. If the enclosure is configured for in-band enclosure management, the processor blade executes the program code to collect the management information. If the enclosure is configured for out-of-band enclosure management, the management module is configured to execute program code for collecting the management information instead of the processor blade.

Enclosure configurable to perform in-band or out-of-band enclosure management

A system having a processor, a printed circuit board, and an adapter board, coupled to the processor through the printed circuit board. The adapter board provides a first signal having a first state when the adapter board is in a proper operating condition and a second state when the adapter board is in an improper condition. The adapter board produces a second signal having the second state for less than a predetermined time when an adapter board requires a reset signal from the processor. The adapter board combines the first signal with the second signal a single signal fed to the processor through the printed circuit board. When the processor detects that the single signal is in the second state for a time less than the predetermined period of time, the process interprets the single signal as indicating the adapter board requires a reset.

Method for communicating plural signals generated at a source to a remote destination through a single wire

System components are managed. Based on a first communication path to a component, first identification information for the component is determined. Based on a second communication path to the component, second identification information for the component is determined. Based on the first identification information and the second identification information, an identity for the component is determined. Based on the identity, a set of tests is performed on the component. Based on the failure rate of the set of tests, it is concluded that another component on the first communication path is faulty.

Managing system components

A data storage system includes a storage processor that is configured to perform load and store operations on a storage array on behalf of external devices. The data storage system also includes a controller that isolates communication between the external devices when coupled to the storage array via the storage processor. The controller further maintains a set of registers that store information associated with the data storage system and allows the storage processor to access the register via an I2C bus. The system utilizes an error detection procedure to allow detection of errors in the data transmitted between the controller and the storage processor. During operation, a checksum value is transmitted between the controller and the storage processor using the I2C bus during a register write or read procedure. The controller and the storage processor utilize the checksum value in an error detection procedure to detect the data errors resulting in transmission of the data by the I2C bus.

Growing community of inventors

Hopkinton, MA, United States of America

Douglas Sullivan