The Data Capacitor II and DC-WAN high-speed file systems at Indiana University

On this page:

• System overview
• Usage policies
• System information
  • Data Capacitor II (DC2)
  • Data Capacitor Wide Area Network (DC-WAN)
• System access
• Listing files
• Sorting files by age
• Transferring files
• Specifying DC2 or DC-WAN as a requirement for your batch job
• Working with protected health information
• Reference
• Acknowledging grant support
• Support

System overview

Usage policies

• The Data Capacitor II and DC-WAN file systems both provide two types of temporary storage space:
  • Scratch space: The DC2 and DC-WAN scratch directories are temporary workspaces available to all users with accounts on IU's research computing systems. Scratch space is not allocated, and its total capacity fluctuates based on project space requirements. Files in scratch space may be purged if they have not been accessed for more than 60 days.

  Your personal scratch directory is automatically created with your user account. It is available at these locations, depending on the file system (replace username with your IU Network ID username):

    /N/dc2/scratch/username
    /N/dcwan/scratch/username
  

  • Project space: DC2 and DC-WAN project space is reserved for projects with atypical requirements that cannot be met by other systems. Requests for project space must be submitted to the High Performance File System (HPFS) team for evaluation by the allocation committee. Files in project space may be purged if they have not been accessed for more than 180 days.

  To request DC2 or DC-WAN project space, submit the Project Allocation Request Form.

• File system space not allocated to projects will be available as scratch space and will vary depending on file system usage.
• Projects receive a default quota of 10 TB. Project owners can request quota increases if additional space is needed. Due to performance issues, storing a large number of small files is discouraged, but arrangements can be made if a need exists.
• The DC2 and DC-WAN file systems are not intended for permanent storage of data and are not backed up. It is your responsibility to arrange any long-term storage required. At IU, to archive data stored or created on the DC2 or DC-WAN file system, move them to IU's Scholarly Data Archive (SDA).
• Lustre is not designed for storing a large number of small files. If you need such storage, you should use a compression utility (e.g., tar or gzip) to bundle your files into a small number of large files. Failure to do so can negatively impact performance of these file systems and strain their file-count (inode) capacities.

System information

Data Capacitor II (DC2)

Data Capacitor Wide Area Network (DC-WAN)

System access

• Data Capacitor II: The DC2 file system is mounted on Big Red II, Karst, and Mason as /N/dc2/, and behaves like any other disk device on those machines. If you have an account on Big Red II, Karst, or Mason, you can access your DC2 scratch directory at (replace username with your IU Network ID username):

    /N/dc2/scratch/username

• DC-WAN: Users at other institutions (including IU researchers with accounts on remote systems) can request DC-WAN storage space, which can be mounted on remote systems, as well as on Big Red II, Karst, and Mason, as /N/dcwan/.

Listing files

You should use ls -l only when necessary, or only on directories containing small amounts of data. Running ls -l in a DC2 or DC-WAN directory to list its contents and associated metadata (e.g., ownership, permissions, and file size information for each file) can cause performance issues for you and other users, particularly if the directory contains a large amount of data.

Due to its parallel architecture, Lustre performs file and metadata operations separately. When you run ls -l in a DC2 or DC-WAN directory, the system contacts Lustre's Metadata Server (MDS) to get your data's location, ownership, and permissions information. However, to retrieve file size information, the system must contact multiple Object Storage Servers (OSSs), which in turn must contact multiple Object Storage Targets (OSTs) that store the data objects that make up your files. When the load on one or more OSS nodes is high, your ls -l command may hang; other users on the file system may experience latency issues, as well.

Furthermore, some IU systems have ls (without any options) aliased to ls --color=tty, which enables the use of colors to distinguish file types. With the alias, running ls initiates a full lookup to determine the color associated with each file, which (as with ls -l) requires communication with the OSSs and the OSTs. Without the alias, running ls contacts the MDS only (i.e., it does not initiate a full lookup involving the OSSs and OSTs). To avoid potential performance issues, you can override the ls --color=tty alias, preventing ls from initiating a full lookup. To do so, add the following line to your shell profile:

  unalias ls

Using ls to list information about individual files creates a lot less overhead on the file system:

• To check for the existence of a file (e.g., my_file), use:

    ls my_file

• To see all details for a specific file (e.g., my_file), use:

    ls -l my_file

Sorting files by age

Data Capacitor II and DC-WAN are intended for temporary storage of research computing data. Files in scratch directories may be purged if they have not been accessed for more than 60 days. Files in project directories may be purged if they have not been accessed for more than 180 days.

To determine which files located in or below the present working directory are the oldest (and at risk of being purged), you can list them by age (oldest to newest) using the find command; for example:

  find . -type f -exec ls -1hltr '{}' +;

In the command above:

• The dot (.) directs find to search the present working directory and its subdirectories.
• The -type f test limits the find search to regular files.
• The -exec ls -1hltr "{}" +; action makes find run the ls command on its search results and treat any subsequent arguments as options to that command until it encounters the semicolon (;) argument.
• The + directive builds a file list from the find search results, appending each file name to the {} string.
• The ls command parses the file list and (given the options provided) displays the results one file per line (-1), in long format (-l), with human-readable file sizes (-h), sorted by modification time (-t), and listed in reverse order (-r).

To perform the same operation on a directory that's not the present working directory, use the same command and options, but replace the dot (.) with the full path to the directory in question; for example:

• For a directory in your scratch space (replace <username> with your Network ID username and some_other_dir with the directory you want to sort):

    find /N/dc2/scratch/<username>/some_other_dir -type f -exec ls -1hltr "{}" +;

• For a directory in your project space, (replace <project_name> with the your project's name and some_other_dir with the directory you want to sort):

    find /N/dc2/projects/<project_name>/some_other_dir -type f -exec ls -1hltr "{}" +;

Transferring files

The Data Capacitor II and DC-WAN file systems are parallel high-performance file systems. Files are not "transferred" to these file system; instead the DC2 or DC-WAN file systems are mounted on computational resources, making them accessible from those resource as directory paths (e.g., /N/dc2/scratch/username). To read or write a file on the DC2 or DC-WAN file system, use the same standard Unix commands used for reading and writing files stored on your computational system's local directories.

Specifying DC2 or DC-WAN as a requirement for your batch job

The Data Capacitor II and DC-WAN parallel file systems are mounted on Big Red II, Karst, and Mason. You can specify either file system as a requirement for batch jobs running on those systems; for instructions, see For batch jobs on Big Red II, Karst, or Mason at IU, how do I specify the required parallel file systems?

Working with protected health information

Your responsibilities

Important: Storing data containing protected health information (PHI) regulated by the Health Insurance Portability and Accountability Act of 1996 (HIPAA) on the DC-WAN file system is not permitted.

If you use the Data Capacitor II file system to store data containing PHI:

• You and/or the project's principal investigator (PI) are responsible for ensuring the privacy and security of that data, and complying with applicable federal and state laws/regulations and institutional policies. IU's policies regarding HIPAA compliance require the appropriate Institutional Review Board (IRB) approvals and a data management plan.
• You and/or the project's PI are responsible for implementing HIPAA-required administrative, physical, and technical safeguards to any person, process, application, or service used to collect, process, manage, analyze, or store PHI.

For more, see When using UITS Research Technologies systems and services, what are my legal responsibilities for protecting the privacy and security of data containing protected health information (PHI)?

Technical safeguards

You should employ the following technical safeguards when working with PHI:

• Set directory permissions: The permissions for a directory containing PHI should be set to grant read, write, and execute access to the owner (you) only. No access at all should be granted to group members and other users.

  To change the permission of an existing file or directory, use the chmod command. For example, to restrict all read and write access to the owner of phi_file, on the command line, enter:

    chmod 700 phi_file

  The above command will set the Unix permissions to look like this:

    -rwx------   1 <username> uits   40 Sep 13 15:12 phi_file

  Alternatively, to configure your user environment so that every new file and directory gets the same permission level (accessible only by the owner), add the following line to your shell profile:

    umask 077

• Encrypt data at rest: While data containing PHI are at rest (i.e., when you are not working with them), they should be encrypted; see Recommended tools for encrypting data containing HIPAA-regulated PHI.

Reference

For more about the Lustre file system, see the Lustre wiki.

Acknowledging grant support

Support