Method and apparatus for test pattern generation

Abstract

A fibre channel switch element that can generate a character or frame based test pattern is provided. The switch element includes a buffer that can be coupled to a transmission protocol engine for sending and receiving data to and from a fibre channel network, wherein the buffer is programmed to generate character or fibre channel frames for testing plural links coupled to the fibre channel switch element while operating in a character or frame mode. The buffer can be coupled to a receive or transmit path and generates characters or frames based on a programmed count to induce real-time errors. The real-time errors include a missing start of frame (“SOF”) and a missing end of frame (“EOF”).

Description

BACKGROUND

1. Field of the Invention

The present invention relates to networks, and more particularly to testing the integrity of communication links.

2. Background of the Invention

In order to test the viability of a communications link in networks, transmitters on the link often contain test pattern generators and receivers on the link often contain test pattern checkers. Each node on a link may also contain a transmitter/receiver pair for bi-directional communications. In this case, the node is generally capable of operating in a loopback mode where the transmitter output is connected to the receiver input. The integrity of the node can be tested in the loopback mode with a transmitter test pattern generator and a receiver test pattern checker.

Conventional test pattern generators and checkers use a pseudo-random pattern, selected to simply verify that a data path is viable and that the received pattern exactly matches the transmitted pattern. A transmitter may also generate a pattern that is unrecognized by the receiver in order to test the checker itself.

Conventional test pattern generators have drawbacks because they are very generic and do not have encoding or protocol details. Hence, these test pattern generators may not be able to induce protocol specific errors.

Therefore, there is a need for a method and system to efficiently test a communication link, rather than rely on standard test pattern generators.

SUMMARY OF THE INVENTION

A fibre channel switch element that can generate a character or frame based test pattern is provided. The switch element includes a buffer that can be coupled to a transmission protocol engine for sending and receiving data to and from a fibre channel network, wherein the buffer is programmed to generate character or fibre channel frames for testing plural links coupled to the fibre channel switch element while operating in a character or frame mode. The buffer can be coupled to a receive or transmit path and generates characters or frames based on a programmed count to induce real-time errors. The real-time errors include a missing start of frame (“SOF”) and a missing end of frame (“EOF”).

To induce a missing SOF, the buffer is started in a character mode and while it is running in the character mode, it is changed to a frame mode. To induce a missing EOF, the buffer starts in a frame mode and then while it is running in the frame mode it changes to a character mode.

In yet another aspect of the present invention, a method for generating test patterns in a fibre channel switch element, using a buffer that can be coupled to plural ports is provided. The method includes, programming the buffer to operate in a character or frame mode; connecting plural ports to receive data from the buffer after the buffer is programmed to operate in the character or frame mode; generating a character stream if programmed to operate in the character mode; and generating a frame if programmed to operate in a frame mode.

This brief summary has been provided so that the nature of the invention may be understood quickly. A more complete understanding of the invention can be obtained by reference to the following detailed description of the preferred embodiments thereof concerning the attached drawings.

BRIEF DESCRIPTION OF THE DRAWINGS

The foregoing features and other features of the present invention will now be described with reference to the drawings of a preferred embodiment. In the drawings, the same components have the same reference numerals. The illustrated embodiment is intended to illustrate, but not to limit the invention. The drawings include the following Figures:

FIG. 1 is a block diagram showing a Fibre Channel network;

FIG. 2 shows a block diagram with a transmit buffer that can be used for generating test patterns, according to one aspect of the present invention;

FIG. 3 is a flow diagram of executable process steps for generating test patterns, according to one aspect of the present invention;

FIG. 4 is a block diagram of a switch element, used according to one aspect of the present invention;

FIG. 5 is a block diagram of a transmission protocol engine, according to one aspect of the present invention; and

FIGS. 6A and 6B show block diagrams of a diagnostic port/SES module, used according to one aspect of the present invention.

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

Definitions:

The following definitions are provided as they are typically (but not exclusively) used in the fibre channel environment, implementing the various adaptive aspects of the present invention.

“AL_PA”: Arbitrated loop physical address.

“CRC”: Cyclic redundancy check code, the last data word in a frame that is transmitted just before the EOF primitive.

“EOF”: End of frame delimiter, a primitive transmitted following the CRC that is transmitted just before the date frame.

“FC-AL”: Fibre channel arbitrated loop process described in FC-AL standard, incorporated herein by reference in its entirety.

“Fibre channel ANSI Standard”: The standard (incorporated herein by reference in its entirety) describes the physical interface, transmission and signaling protocol of a high performance serial link for support of other high level protocols associated with IPI, SCSI, IP, ATM and others.

“FC-1”: Fibre channel transmission protocol, which includes serial encoding, decoding and error control.

“FC-2”: Fibre channel signaling protocol that includes frame structure and byte sequences.

“FC-3”: Defines a set of fibre channel services that are common across plural ports of a node.

“FC-4”: Provides mapping between lower levels of fibre channel, IPI and SCSI command sets, HIPPI data framing, IP and other upper level protocols.

“LIP”: Loop initialization protocol primitive.

“L_Port”: A port that contains Arbitrated Loop functions associated with the Arbitrated Loop topology.

“Primitive”: A 32-bit control word.

“SES”: SCSI Enclosure Services.

“SOF”: Start of Frame delimiter, a primitive transmitted to designate the beginning of a data frame.

“TPE”: Transmission Protocol Engine, a controller that operates at the FC-1level.

To facilitate an understanding of the preferred embodiment, the general architecture and operation of a fibre channel system will be described with a brief introduction to fibre channel standard terminology. It is noteworthy that the various inventive aspects of the present invention are not just limited to fibre channel based networks and can be used in other network environments, for example, Ethernet/IEEE802.3. The specific architecture and operation of the preferred embodiment will then be described with reference to the general architecture of the fibre channel system.

Fibre channel is a set of American National Standard Institute (ANSI) standards, which provide a serial transmission protocol for storage and network protocols such as HIPPI, SCSI, IP, ATM and others. Fibre channel provides an input/output interface to meet the requirements of both channel and network users.

Fibre channel supports three different topologies: point-to-point, arbitrated loop and fibre channel fabric. The point-to-point topology attaches two devices directly. The arbitrated loop topology attaches devices in a loop. The fibre channel fabric topology attaches host systems directly to a fabric, which are then connected to multiple devices. The fibre channel fabric topology allows several media types to be interconnected.

Fibre channel is a closed system that relies on multiple ports to exchange information on attributes and characteristics to determine if the ports can operate together. If the ports can work together, they define the criteria under which they communicate.

In fibre channel, a path is established between two nodes where the path's primary task is to transport data from one point to another at high speed with low latency, performing only simple error detection in hardware.

In fibre channel, a device (e.g. device A) seeking access to another device (device B) sends an OPN primitive (after it wins arbitration) and establishes a connection with device B. Device B sends an R_RDY primitive indicating that credit is available for a frame. Thereafter, frames are transferred.

FIG. 1 is a block diagram of a fibre channel system 100 implementing the methods and systems in accordance with the adaptive aspects of the present invention. System 100 includes plural devices that are interconnected. Each device includes one or more ports, classified as node ports (N_Ports), fabric ports (F_Ports), and expansion ports (E_Ports). Node ports may be located in a node device, e.g. server 103, disk array 105 and storage device 104. Arbitrated loop 106 may be operationally coupled to switch 101 using arbitrated loop ports (FL_Ports).

The devices of FIG. 1 are operationally coupled via “links” or “paths”. A path may be established between two N_ports, e.g. between server 103 and storage 104. A packet-switched path may be established using multiple links, e.g. an N-Port in server 103 may establish a path with disk array 105 through switch 102.

FIG. 4 is a block diagram of an 18-port ASIC FC element 400A (also referred to as system 400A) according to one aspect of the present invention. FC element 400A provides various functionality in an FC_AL environment, including without limitation, FC element 400A operates as a loop controller and loop switch using switch matrix 408, in accordance with the FC-AL standard.

FC element 400A of the present invention is presently implemented as a single CMOS ASIC, and for this reason the term “FC element” and ASIC are used interchangeably to refer to the preferred embodiments in this specification. Although FIG. 4 shows 18 ports, the present invention is not limited to any particular number of ports.

System 400A provides a set of port control functions, status indications, and statistics counters for monitoring the health of the loop and attached devices, diagnosing faults, and recovering from errors.

ASIC 400A has 18 ports where 16 ports are shown as numeral 405 while a host port 404 and cascade port 404A are shown separately for convenience only. These ports are generic to common Fibre Channel port types, for example, L_Ports.

For illustration purposes only, all ports are drawn on the same side of ASIC 400A in FIG. 4. However, the ports may be located on any side of ASIC 400A. This does not imply any difference in port or ASIC design. Actual physical layout of the ports will depend on the physical layout of the ASIC.

Each port has transmit and receive connections to switch matrix 408 and includes transmit protocol engine 407 and a serial/deserializer 406. Frames enter/leave the link 405A and SERDES 406 converts data into 10-bit parallel data to fibre channel characters.

Switch matrix 408 dynamically establishes a connection for loop traffic. Switch matrix 408 includes a global arbiter (hence switch matrix 408 is also referred to as SGA 408) that provides lower latency and improved diagnostic capabilities while maintaining full Fibre Channel Arbitrated Loop (FC-AL) compliance.

Switch matrix 408 provides a quasi-direct architecture in the form of a buffer-less Switch Matrix. Switch matrix 408 includes data multiplexers that provide a path to each port.

SGA 408 creates a direct loop connection between source and destination devices. This connection methodology avoids the delay associated with data having to pass from one disk drive member of the loop to the next until the data has completed traversing the loop.

System 400A includes plural I2C (I2C standard compliant) interfaces 412-413 that allow system 400A to couple to plural I2C ports each having a master and slave capability.

System 400A also includes a general purpose input/output interface (“GPIO”) 415. This allows information from system 400A to be analyzed by any device that can use GPIO 415. Control/Status information 419 can be sent or received through module 415.

System 400A also includes a SPI module 414 that is used for parallel to serial and serial to parallel transfer between processor 400 firmware and flash memory 421 in the standard Little Endian format.

System 400A also includes a Universal Asynchronous Receiver/Transmitter (“UART”) interface 418 that converts serial data to parallel data (for example, from a peripheral device modem or data set) and vice-versa (data received from processor 400) complying industry standard requirements.

System 400A can also process tachometer inputs (received from a fan, not shown) using module 417. Processor 400 can read the tachometer input via a tachometer rate register and status register (not shown). Timer module 411 is used to monitor plural timers (not shown) used by System 400A.

System 400A provides pulse width modulator (“PWM”) outputs via module 416. Processor 400 can program plural outputs.

Processor 400 can access runtime code from memory 420 and input/output instructions from read only memory 409.

System 400A also includes two frame manager modules 402 and 403 that are similar in structure.

Module 402 (also referred to as the “diag module 402”) is a diagnostic module used to transfer diagnostic information between a FC-AL and the firmware of system 400A.

Diag module 402 is functionally coupled to storage media (via ports 405) via dedicated paths outside switch matrix 408 so that its connection does not disrupt the overall loop. Diag module 402 is used for AL_PA capture during LIP propagation, drive(s) (coupled to ports 405) diagnostics and frame capture.

Module 403 (also referred to as “SES module 403”) complies with the SES standard and is functionally coupled to host port 404 and its output is routed through switch matrix 408. SES module 403 is used for in-band management services using the standard SES protocol.

When not bypassed, modules 402 and 403 receive primitives, primitive sequences, and frames. Based on the received traffic and the requests from firmware, modules 402 and 403 maintain loop port state machine (LPSM) (615, FIG. 6B) in the correct state per the FC-AL standard specification, and also maintains the current fill word.

Based on a current LPSM 615 state (OPEN or OPENED State), modules 402 and 403 receive frames; pass the frame onto a buffer, and alert firmware that a frame has been received. Module 402 and 403 follow FC-AL buffer-to-buffer credit requirements.

Firmware may request modules 402 and 403 to automatically append SOF and EOF to the outgoing frame, and to automatically calculate the outgoing frame's CRC using CRC generator 612. Modules 402 and 403 can receive any class of frames and firmware may request to send either fibre channel Class 2 or Class 3 frames.

Port Management Interface (PMIF) 401 allows processor 400 access to various port level registers, SerDes modules 406 and TPE Management Interfaces 509 (FIG. 5). PMIF 401 contains a set of global control and status registers, receive and transmit test buffers, and three Serial Control Interface (SCIF) controllers (not shown) for accessing SerDes 406 registers.

FIGS. 6A and 6B show block diagrams for module 402 and 403. It is noteworthy that the structure in FIGS. 6A and 6B can be used for both modules 402 and 403. FIG. 6B is the internal data path of a FC port 601 coupled to modules 402/403.

Modules 402 and 403 interface with processor 400 via an interface 606. Incoming frames to modules 402 and 403 are received from port 601 (which could be any of the ports 404, 404A and 405) and stored in frame buffer 607. Outgoing frames are also stored in frame buffer 607.

Modules 402 and 403 have a receive side memory buffer based on “first-in, first-out” principle RX_FIFO, (“FIFO”) 603 and transmit side TX_FIFO FIFO 604 interfacing with FIFO 605. A receive side FIFO 603 signals to firmware when incoming frame(s) are received. A transmit side FIFO 604 signals to hardware when outgoing frames(s) are ready for transmission. A frame buffer 607 is used to stage outgoing frames and to store incoming frames. Modules 602 and 602A are used to manage frame traffic from port 601 to buffers 603 and 604, respectively.

Modules 402 and 403 use various general-purpose registers 608 for managing control, status and timing information.

Based on the AL_PA, modules 402 and 403 monitor received frames and if a frame is received for a particular module (402 or 403), it will pass the frame onto a receive buffer and alert the firmware that a frame has been received via a receive side FIFO 603. Modules 402 and 403 follow the FC-AL buffer-to-buffer credit requirements using module 616. Modules 402 and 403 transmit primitives and frames based on FC-AL rules. On request, modules 402 and 403 may automatically generate SOF and EOF during frame transmission (using module 613). On request, modules 402 and 403 may also automatically calculate the Cyclic Redundancy Code (CRC) during frame transmission, using module 612.

Overall transmission control is performed by module 611 that receives data, SOF, EOF and CRC. Transmit buffer control is provided by module 614. A word assembler module 609 is used to assemble incoming words, and a fill word module 610 receives data “words” before sending it to module 611 for transmission.

FIG. 5 shows a block diagram of the transmission protocol engine (“TPE”) 407. TPE 407 maintains plural counters/registers to interact with drives coupled to ports 405. Each TPE 407 interacts with processor 400 via port manager interface 401.

Each Fibre Channel port of system 400A includes a TPF module for interfacing with SerDes 406. TPE 407 handles most of the FC-1layer (transmission protocol) functions, including 10B receive character alignment, 8B/10B encode/decode, 32-bit receive word synchronization, and elasticity buffer management for word re-timing and TX/RX frequency compensation.

SerDes modules 406 handle the FC-1serialization and de-serialization functions. Each SerDes 406 port consists of an independent transmit and receive node.

TPE 407 has a receive module 500 (that operates in the Rx clock domain 503) and a transmit module 501. Data 502 is received from SERDES 406 and decoded by decoding module 504. A parity generator module 505 generates parity data. SGA interface 508 allows TPE to communicate with switch 514 or switch matrix 408. Interface 508 (via multiplexer 507) receives information from a receiver module 506 that receives decoded data from decode module 504 and parity data from module 505.

Management interface module 509 interfaces with processor 400. Transmit module 501 includes a parity checker 511, a transmitter 510 and an encoder 512 that encodes 8-bit data into 10-bit data. 10-bit transmit data is sent to SERDES 406 via multiplexer 513.

Like Gigabit Ethernet and some other serial protocols, Fibre Channel uses 8B/10B data character encoding and decoding i.e. 8-bit data bytes are encoded into 10-bit characters for transmission; and 10-bit characters are decoded into 8-bit data bytes upon reception.

System 400A includes two character buffers—a 10B transmit character buffer (TXCB) 208 (See FIG. 2) that can be connected to the output(s) of any or all TPE transmitters and an 8B receive character buffer (RXCB) (not shown) that can be connected to the output(s) of any or all TPE receivers. RXCB operates at the 8B level and its operation is similar to TXCB 208.

As shown in FIG. 2, 8-bit data 204 is received by an encoder 205 located in TPE 407 that converts 8-bit data to 10-bit and then the converted data is passed through multiplexer 206 and transmitted as 10-bit data 207 via SERDES 406.

Serial data 200 is received and passed to error checker/decoder module 202 via a multiplexer 201. Serial data is converted to 8-bit by module 202 and then sent out as 8-bit data 203.

TXCB 208 includes plural 10-bit wide memory locations that can each contain any 10B character. The locations in TXCB 208 can be output in two modes, character mode or frame mode. In the character mode, TXCB 208 continually outputs each location in TXCB 208 sequentially, wrapping to the first location when the last location is reached until it is either stopped by firmware or a programmable termination count has expired.

In the frame mode, TXCB 208 reserves three locations for SOF, CRC, and EOF values that are each output at the appropriate position in the data stream to form a fibre channel frame. As in character mode, TXCB 208 outputs the remaining locations sequentially, wrapping from the last unreserved location to the first.

As stated above, TXCB 208 runs until it is either stopped by firmware or until a programmable termination count has expired. A counter (not shown) may be implemented to count characters or to count 4-character words as implemented in Fibre Channel as the smallest valid transmission entity. In one aspect of the present invention, system 400A uses a word counter to count TXCB 208 transmission.

Prior to starting TXCB 208 with a control register bit (located at port manager interface 401), normal transmission traffic (200) is driven to SERDES 406 as shown in FIG. 2. When the control register bit is set to start TXCB 208, any TPE 407 programmed to be connected to TXCB 208 is connected to TXCB 208.

If the counter is programmed with a non-zero value when TXCB 208 is started, it will count down to zero and then TXCB 208 stops outputting characters and is disconnected from the TPE(s)407 allowing normal transmission traffic to SERDES 406.

If the counter is programmed with a value of zero when TXCB 208 is started, it runs until firmware stops it by writing a control register bit.

When TXCB 208 runs in frame mode, the TXCB will first output the value in the reserved SOF field. Next the unreserved values are cycled through as frame data until the counter value indicates that the last frame data word is required and the value in the reserved CRC field is output followed by the value in the reserved EOF field. For convenience, the count value in system 400A does not include the SOF and EOF values but includes the CRC value. Only the data between the frame delimiters is valid frame data.

The TXCB mode of operation, character or frame, can be changed in real time by firmware to induce framing errors. These errors include missing SOF and missing EOF. To induce a frame that is missing both delimiters, SOF and EOF, character mode is used with TXCB 208 filled with data values only —no SOF or EOF primitives are programmed into TXCB 208.

To induce a missing EOF, TXCB 208 is started in frame mode then, while it is still running, firmware changes it to character mode. It can then be stopped under firmware control or by count termination. The value in the reserved CRC field and the EOF field is not output.

To induce a missing SOF, TXCB 208 is started in character mode and while it is still running, firmware changes it to frame mode. To support inducing a missing SOF, TXCB 208 can be programmed to cycle only through the unreserved fields while in character mode so that the values in the reserved CRC and EOF fields are not output prematurely. In order to induce a missing SOF, the TXCB is count-terminated so that it can determine when to output the values in the reserved CRC and EOF fields.

In addition to generating valid frames and character streams, TXCB 208 can also generate the following errors:

Invalid Transmission Words which occur when a word contains at least one of the following errors:

• • 10B encoding errors;
  • 10B disparity errors;
  • Beginning running disparity errors;
  • Invalid special code alignment errors (K errors);
  • Losses of character sync;
  • Losses of word sync;
  • Link failures;
  • CRC errors;
  • Frame too short errors;
  • Frame too long errors;
  • Missing SOF errors;
  • Missing EOF errors; and
  • Delimiter errors.

It is noteworthy that the present invention is not limited to TXCB 208 generating any particular error(s).

The foregoing errors are detected in the receive section of a TPE 407 and counted in the TPE MIF 509. The number of received frames and words within frames are counted.

FIG. 3 shows a flow diagram of executable process steps, according to one aspect of the present invention. In step S300, TXCB 208 is programmed to generate either characters or a frame.

In step S301, all the TPEs (407) are programmed to be operationally coupled to TXCB 208.

In step S302, the character or frame mode is selected.

In step S303, the process chooses either a counter-based count or firmware control to stop TXCB 208. As discussed above, with respect to FIG. 2, if the counter is programmed with a non-zero value when TXCB 208 is started, it will count down to zero and then TXCB 208 stops outputting characters and is disconnected from the TPE(s)407 allowing normal transmission traffic to SERDES 406. If the counter is programmed with a value of zero when TXCB 208 is started, it runs until firmware stops it by writing a control register bit.

In step S304, TXCB 208 generates characters, if the character mode was chosen in step S302. If frame mode is selected, then TXCB generates a frame in step S305.

In step S306, the process stops, either based on a count or firmware.

In one aspect of the present invention, a test pattern generator is provided that can generate valid and invalid patterns at character and frame level to test overall network integrity and operation.

Although the present invention has been described with reference to specific embodiments, these embodiments are illustrative only and not limiting. For example, the foregoing system is not limited to fibre channel alone, and can be used in Ethernet/IEEE802.3 based networks as well. Many other applications and embodiments of the present invention will be apparent in light of this disclosure and the following claims.

Claims

1. A fibre channel switch element configured to generate both character- and frame-based test patterns, the switch element comprising: a buffer configured to be coupled to a transmission protocol engine (TPE) for sending and receiving data to and from a fibre channel network and for testing at least one link coupled to the fibre channel switch element;wherein the buffer is programmed to generate characters when operating in a character mode and to generate fibre channel frames when operating in a frame mode; andthe buffer is further configured to run in character mode and to be changed, while running in character mode, to frame mode in order to induce a protocol-specific error; andthe buffer is further configured to run in frame mode and to be changed, while running in frame mode, to character mode in order to induce a protocol-specific error.

2. The fibre channel switch element of claim 1, wherein the buffer is configured to be coupled to a receive path or a transmit path of the TPE.

3. The fibre channel switch element of claim 1, wherein the buffer is configured to generate characters or frames based on a programmed count.

4. The fibre channel switch element of claim 1, wherein the buffer is configured to generate characters or frames under firmware control.

5. The fibre channel switch element of claim 1, wherein the protocol-specific errors occur in real time.

6. The fibre channel switch element of claim 1, wherein the protocol-specific errors include at least one of a missing start of frame (SOF) and a missing end of frame (EOF).

7. The fibre channel switch element of claim 6, wherein to induce a missing SOF the buffer is started in a character mode and, while it is running in the character mode, it is changed to a frame mode.

8. The fibre channel switch element of claim 6, wherein to induce a missing EOF, the buffer starts in a frame mode and, while it is running in the frame mode, it changes to a character mode.

9. A method for generating both character- and frame-based test patterns in a fibre channel switch element using a buffer configured to be coupled to at least one port, the method comprising the steps of: programming the buffer to operate in a character mode;connecting the at least one port to the buffer to receive data from the buffer after the buffer is programmed to operate in the character mode;the buffer generating a character stream; andas the buffer is generating the character stream, the buffer is changed from the character mode to a frame mode in order to induce a protocol-specific error.

10. The method of claim 9, wherein the protocol-specific error is a missing start of frame.

11. The method of claim 9, wherein the buffer generates characters based on a programmed count.

12. The method of claim 9, wherein the buffer generates characters under firmware control.

13. The method of claim 9, wherein the protocol-specific error occurs in real time.

14. A method for generating both character- and frame-based test patterns in a fibre channel switch element using a buffer configured to be coupled to at least one port, the method comprising the steps of: programming the buffer to operate in a frame mode;connecting the at least one port to the buffer to receive data from the buffer after the buffer is programmed to operate in the frame mode;the buffer generating a frame; andas the buffer is generating the frame it is changed from the frame mode to a character mode in order to induce a protocol-specific error.

15. The method of claim 14, wherein the protocol-specific error is a missing end of frame.

16. The method of claim 14, wherein the buffer generates the frame based on a programmed count.

17. The method of claim 14, wherein the buffer generates the frame under firmware control.

18. The method of claim 14, wherein the protocol-specific error occurs in real time.