In a storage network including at least a computer system, at least an external storage and at least a network system for communication of input/output data between the computer system and the external storage, a method of collecting the performance data on the network system and the software operated on the network system, in which the range or degree of data collection is automatically adjusted as required based on the performance data collected.

Method and program of collecting performance data for storage network

Embodiments of the invention provide an expert analysis method for analyzing a network. The method includes capturing at least one bidirectional data trace from the network, determining a network topology, analyzing protocols in conversations between initiators and targets to determine if the protocols are valid using the determined network topology and known protocol standards, and displaying at least one of errors or warnings determined in the protocol and metrics calculated from the analysis of the protocols to a user.

Network expert analysis process

Methods and apparatus for implementing storage virtualization on a network device of a storage area network are disclosed. A virtual enclosure is created that has one or more virtual enclosure ports and is adapted for representing one or more virtual storage units. Each of the virtual storage units represents one or more physical storage locations on one or more physical storage units of the storage area network. Each of the virtual enclosure ports of the virtual enclosure is associated with a port of a network device within the storage area network. An address or identifier is then assigned to each of the virtual enclosure ports.

Methods and apparatus for implementing virtualization of storage within a storage area network through a virtual enclosure

A performance information display method using a computer, includes the steps, in the computer, of reading out information data of a storage device previously stored in a storage device and information data of a plurality of devices utilizing the storage device, displaying an identifier of the storage device and identifiers of a plurality of devices utilizing the storage device on a screen on the basis of the information data read out, accepting a command to select the displayed identifier of the storage device, and displaying performance information data of the devices utilizing the selected storage device in association on the basis of the accepted command and the information data read out.

Method for analyzing performance information

A data storage system according to certain aspects can share a single snapshot for multiple applications and/or agents. For example, the data storage system can receive snapshot commands from multiple applications and/or agents, and can group them for a single snapshot (e.g., based on time of receipt of the snapshot commands). Data associated with the multiple applications and/or agents may reside on a single LUN or volume. The data storage system can take a single snapshot of the LUN or volume, and generate metadata regarding which portion of the snapshot is related to which application. The single snapshot can be stored in one or more secondary storage devices. The single snapshot may be partitioned into portions relating to different applications and stored separately.

Single snapshot for multiple agents

Embodiments of the invention may further provide a method for adjusting the granularity of a network analysis sample while maintaining validity. The method includes calculating states for each device in the network for a first number of predetermined equal intervals within a first sample window, selecting a second sample window that is smaller than the first sample window, selecting a second predetermined number of equal intervals for the second sample window, and determining an interval from the first number of predetermined intervals that immediately precedes an initial interval of the second predetermined number of equal intervals. The method further includes using the calculated state from the preceding interval to calculate a starting state for the initial interval, and calculating state for each device in the network for each of the second predetermined number of equal intervals.

Network analysis sample management process

Embodiments of the invention provide a method for determining errors and metrics in a computer network. The method includes positioning an analyzer in communication with the network, capturing a data trace of the network with the analyzer, determining a network device topology from a first processing of the data trace, building user layer protocols using a second processing of the data trace and the determined device topology, determining errors in the network device topology using protocol experts applied to the user layer protocols in conjunction with the determined device topology, and displaying at least one of the device topology and the determined errors to a user.

Network analysis tool

Embodiments of the invention provide a method for analyzing a data trace representative of an FC network. The method includes determining a topology of the network, filtering the data trace for open commands that are not perceived by at least one analyzer positioned in communication with the network and eliminating devices associated with these open commands not received by an analyzer from further analysis, filtering the data trace for failed open commands and eliminating devices associated with the failed open commands from further analysis, and filtering the trace data for frames to destinations that are not received by the analyzer and eliminating devices associated with these frame from further analysis. The method further includes filtering frames transmitted when a loop is in closed state and eliminating devices associated with transmitting frames when a loop is closed from further analysis, and conducting error analysis of the network topology not eliminated by a filtering step.

Network analysis omniscent loop state machine

Embodiments of the invention provide a scalable method for analyzing a network. The method includes generating a data trace representative of the network, determining a topology for the network from the data trace, and sequentially analyzing each frame in the data trace to determine at least one of network errors, warnings, and metrics. The analysis of each frame generally includes analyzing a first protocol layer of the frame with a first expert engine, determining if a second protocol layer is present in the frame, passing the frame to a second expert engine, and passing the frame to additional expert engines if the frame contains additional protocol layers.

Timothy Lane McDaniel

Papers

Network expert analysis process

Network analysis sample management process

Network analysis tool

Network analysis omniscent loop state machine

Network analysis scalable analysis tool for multiple protocols