Lsi Logic Corporation

Lsi Corporation

Mark Slutz

David T Uddenberg

William W Voorhees

William J Schmitz

Erik Paulsen

Carl Edward Gygi

Brian J Varney

David W So

Stuart L Nuffer

Methods and structures within a SAS expander for detecting link level errors in PHYs of a SAS expander to reduce overhead bandwidth utilization of SAS links between SAS initiators and SAS expanders. In one aspect hereof, a SAS expander self monitors the error status registers of its own PHYs over an internal path that does not use bandwidth of the attached SAS links. When a link level error is so detected the SAS expander may initiate actions and/or report the error to a SAS initiator to thereby reduce the potential for lost data integrity. Where multiple SAS expanders are configured in a SAS domain fabric, each expander may monitor its PHYs or one expander may be designated a master and monitor PHYs of all expanders in the fabric.

Methods and structure for detecting SAS link errors with minimal impact on SAS initiator and link bandwidth

Methods and structures within a SAS expander for testing SAS devices and other SAS expanders in the SAS domain. Testing devices and expanders in the domain by operations performed within a SAS expander in the domain relieves the burden of such processing in attached host systems and adds flexibility for scheduling processing for test operation of devices and expanders in the domain. In one aspect hereof, the testing may be performed by a master SAS expander configured in the domain. The SAS expander may initiate testing of devices following completion of the SAS discovery process. Testing may also be initiated in response to events in the SAS domain not typically detected by attached host systems.

Methods and structure for verifying domain functionality

Methods and structures within a SAS expander for initiating communication with one or more SAS initiators in a SAS domain to inform the initiators of sensed changes in the domain without the need for a full SAS Discovery process. In one aspect hereof, the expander may transmit a vendor unique BROADCAST primitive to inform SAS initiators that they should initiate a vendor unique SMP or SSP exchange with the expander to determine changes to the SAS domain. In another aspect hereof, the SAS initiator may respond as an SMP or SSP target device in response to initiation of vendor unique SMP or SSP exchanges by the expander. The expander may report to initiators regarding sensed changes in the domain and/or statistics regarding operation of the expander or other elements of the domain.

Methods and structure for SAS expander initiating communication to a SAS initiator to identify changes in the SAS domain

The present invention is a method and system for providing a complete validation of an initiator and target within bus architecture. A target's behavior may be controlled by an initiator. Control of the target may be through execution of initiator commands including vendor unique commands relating to desired characteristics for testing. The initiator's response to the target's behavior may be verified due to the handshaking communication protocol between a target and initiator. Additionally, by altering the behavior of the target to test initiator response, a target's behavior is also validated.

Method and apparatus for controlling SAS/fibre target behavior from a host

Methods and associated structure for utilizing multiple ports or PHYs comprising a SAS wide port to improve transmission bandwidth utilization for a single large I/O request. In one aspect hereof, a large I/O request is broken into a plurality of smaller I/O requests to be distributed over multiple PHYs or ports of a configured wide SAS port. The number of smaller I/O requests may be any number up to the maximum number of PHYs or ports comprising the SAS wide port. In another aspect hereof, the size of a large I/O request may be compared against a threshold value to determine whether the large request should be broken into smaller requests. The threshold value may be determined in accordance with features and aspects hereof either statically or dynamically based on workloads assigned to, and utilization of, the configured SAS wide port.

Methods and structure for improved transfer rate performance in a SAS wide port environment

Improved methods and structures for testing of SAS components, in situ, in a SAS domain. A first SAS component is adapted to generate stimuli such as error conditions to elicit a response to the error condition from a second SAS component coupled to the first in the intended SAS domain configuration. In one aspect, a SAS device controller generates stimuli applied to a SAS expander coupled thereto and verifies proper response from the SAS expander. In another aspect, a SAS expander generates stimuli applied to a SAS device controller coupled thereto and verifies proper response from the SAS device controller. Stimuli may be generated by custom circuits or firmware/software within the first component. Vendor specific SAS SMP transactions may be used to cause the first component to enter the special verification mode.

Methods and structure for testing responses from SAS device controllers or expanders

A system and method for testing the signals on a parallel communication bus uses a single printed circuit board that connects to the bus. The signals from the bus may be passively and actively filtered prior to a multiplexer. The multiplexer may be controlled by a variety of inputs, including communications over a second bus by a remote device. The output of the multiplexer is one or more probe points that may be connected to a measurement device.

Parallel bus debugging tool

A method and apparatus for generating a CRC (cyclic redundancy check)/parity error in network environment. A SCSI (small computer systems interface) bus expander such as an Ultra320 bus expander or the like is added between a sending device and a receiving device. The sending device-receiving device pair may execute a training session to determine the skew compensation. During the training session, the SCSI bus expander may figure out timing differences due to skew and adjusts the timing of each data signal to compensate for skew. For each data signal, a compensated time may be obtained. The compensated time may then be modified through a JTAG (Joint Test Action Group) port of the SCSI bus expander. The compensated times may be adjusted such that a CRC/parity error is generated on every I/O (input/output) or just some I/Os to the receiving device. By intentionally generating a CRC/parity error, the response of the devices in the SCSI environment to a CRC/parity error may be evaluated during an input/output (I/O) test.

Method and apparatus for generating CRC/parity error in network environment

A method for data verification in a data storage environment including the steps of (A) sending a command from an initiator to a target, where the command defines an expected data pattern, (B) sending a block write command from the initiator to the target, where the write command initiates sending data from the initiator to the target, (C) comparing data received to the expected data pattern and (D) generating a status indication in response to the comparison.

Method and/or apparatus for SCSI target verification

Systems and methods for analyzing data transferred through an SPI data bus are presented. In one exemplary preferred embodiment of the invention, an SPI data probe imitates an SPI device coupled to the SPI data bus and receives data from the SPI data bus so that the data may be analyzed. The SPI data probe transfers the data to an analysis unit without substantially altering impedance more than the SPI device would. The SPI data probe includes connectors configured for coupling the probe to the SPI data bus and for coupling the probe to an analysis unit. The SPI data probe also includes circuitry that may buffer, compensate and deskew the data as an SPI device would.

Systems and methods for analyzing data of an SPI data bus

Disclosed is a method for automatically testing the deskew setting for the clock in a parallel data interface. The deskew value is varied to a high and a low limit to the point where errors occur when transmissions occur. After determining the high and low operable limits of the deskew values, an optimum deskew setting may be determined and set for the system. The present invention may be used as a design verification technique, for optimizing a system after integration, or for further optimization of the deskew value after performing a training pattern for optimizing transmission performance.

Method for determining deskew margins in parallel interface receivers

A communications layer is provided between a host-based SCSI initiator and a SCSI target device to fully automate the validation process. The communications layer allows the host to direct variation and modification of the target parameters and behavior using vendor unique commands. The behavioral modification aims to establish interoperability by conforming the behavior of the target to the host behavior. The host-based initiator transports a suitable command structure to the target device containing appropriate ones of the vendor unique commands and associated parameter data. The target executes and otherwise processes the command structure to effectuate a reconfiguration according to the specifics of the command code. The command code is sufficient to fully reconfigure the SCSI target. Accordingly, the reconfiguration process is carried out in a fully automated fashion.

Growing community of inventors

Colorado Springs, CO, United States of America

Mark Slutz