UniTree System Summary and Connection Information

User Information Home
Compute Resources
Software
Data
Security
Allocations
Consulting
Training
Strategic Applications Program

Table of Contents

1. System Overview
2. Connecting to UniTree
3. Using UniTree

System Overview

UniTree, NCSA's Mass Storage System, is available to all NCSA users for permanent storage of data. Your UniTree login is the same as that on the NCSA production machines; however, logging onto UniTree via ssh is not currently supported. Users must use one of the access methods described below.

UniTree is a high-speed, large-capacity data storage system for NCSA and TeraGrid users. It consists of a high-performance system running DiskXtender software, which implements the IEEE Mass Storage Reference Model. This resource provides users with a network-centered, parallel storage system capable of unlimited storage capacity. Users may store files here permanently and confidently because backup of data is automatically done within this storage system. Two copies of each file are made without requiring user interaction.

System Profile

• SGI Origin 3900 running IRIX64 version 6.5.x
• 16 700 MHZ IP35 Processors
• 12 GB of memory
• 10 1 Gb ethernet connections
• 2 10 Gb ethernet connections
• 35 TB first level disk cache
• DiskXtender 2.9 from EMC/Legato
• Locally developed GridFTP and Kerberos FTP services

Connecting to UniTree

Each of NCSA's production resources has a dedicated, high-speed connection to UniTree. To utilize these internal connections simply use the mssftp or msscmd, or designate the appropriate host names as illustrated below.

NCSA's mass storage system can be accessed both from outside the NCSA domain and from NCSA's production machines at mss.ncsa.uiuc.edu (on Radium, Copper and Tungsten) and at mss.ncsa.teragrid.org (on Mercury and Cobalt). Users can initiate transfers using mssftp (msscmd), uberftp, globus-url-copy, the tgcp command and other Kerberos-enabled FTP clients.

UniTree can be accessed remotely via one of its FTP interfaces using Kerberos, GSI or NCSA HPC passwordless authentication. The options available for authentication depend upon where you are connecting from. GSI clients include globus-url-copy, gsincftp and UberFTP. Users must obtain X.509 credentials and maintain a valid proxy certificate to use GridFTP (GSI authenticated) clients. Refer to The TeraGrid Proxy Information Page for details. The passwordless client available only from NCSA HPC systems is mssftp. The Kerberos client is named ftp on most systems. Check with your system administrator to determine if the default ftp on your system is indeed "kerberized".

Below are several common programs used to access UniTree:

ftp mss.ncsa.uiuc.edu

This needs to be the kerberized ftp client (/usr/local/krb5/bin/ftp on NCSA production machines). See NCSA's Security page for information on installing Kerberos on your local machine. mssftp and msscmd (described below) are recommended for accessing MSS from NCSA production machines since they provide better performance and automatically authenticate.

mssftp

The mssftp command is available on all NCSA production machines. Invoking the mssftp command will automatically connect you to UniTree without the need to enter a login name or password. Once connected, the interface is similar to most text-based ftp clients with an enhanced command set that provides additional functionality on MSS. Refer to man mssftp for more information.

msscmd

The msscmd command provides a command line interface to mssftp. It available on all NCSA production machines and can be used both interactively and in batch scripts (see man msscmd).

uberftp

The uberftp client is available on all NCSA production machines and is free to download. uberftp supports GSI and MSS (NCSA passwordless) authentication and GridFTP enhancements such as parallel streams. uberftp supports command line arguments and interactive use.

globus-url-copy

The globus-url-copy file transfer client is available on Mercury and Cobalt. globus-url-copy is a command line tool used to initiate file transfers by specifying source and destination URLs. globus-url-copy uses GSI authentication and will initiate a passwordless file transfer between sites over which a valid grid proxy has been issued.

tgcp

The tgcp (TeraGrid copy) command is a wrapper that invokes globus-url-copy after querying a set of configuration files which fill in grid specific optimizations (such as TCP buffer size) for all possible transfers on TeraGrid. In addition, tgcp provides a more forgiving syntax than globus-url-copy and can be invoked similarly to the scp command.

Note: The UniTree User Guide contains a sample UniTree FTP session.

Using UniTree

Results from production, important input data and other project related data can be placed in MSS permanently. Data purge policies, applying to scratch space, are in place on most production machines at NCSA. Freeing up scratch file systems by moving data to MSS is in the user communities' best interest and is the only way to permanently store large amounts of data that exceed the home directory quota. Data can be staged in and out of MSS manually or using batch script commands.

On the NCSA IBM p690 and the SGI Altix, the saveafterjob utility is available for automated, guaranteed saving of files from batch jobs to mass storage. Users writing thier own job scripts should specify the $SCR environment variable as the destination file system for the job.

Important Note: Be sure to specify all files that need to be saved to saveafterjob. The default behavior of saveafterjob is to purge the temporary job directory upon successful transfer of the specified files. See the document Automated Saving of Files from Batch Jobs for more information.

Getting Further Assistance

If you require further assistance, send e-mail to one of the following addresses:

• help@teragrid.org (TeraGrid Users)
• help@ncsa.uiuc.edu (NCSA HPC Users)