Storage and file management

From Alliance Doc
Jump to navigation Jump to search
This site replaces the former Compute Canada documentation site, and is now being managed by the Digital Research Alliance of Canada.

Ce site remplace l'ancien site de documentation de Calcul Canada et est maintenant géré par l'Alliance de recherche numérique du Canada.

Other languages:

Overview[edit]

We provide a wide range of storage options to cover the needs of our very diverse users. These storage solutions range from high-speed temporary local storage to different kinds of long-term storage, so you can choose the storage medium that best corresponds to your needs and usage patterns. In most cases the filesystems on our systems are a shared resource and for this reason should be used responsibly because unwise behaviour can negatively affect dozens or hundreds of other users. These filesystems are also designed to store a limited number of very large files, which are typically binary since very large (hundreds of MB or more) text files lose most of their interest in being readable by humans. You should therefore avoid storing tens of thousands of small files, where small means less than a few megabytes, particularly in the same directory. A better approach is to use commands like tar or zip to convert a directory containing many small files into a single very large archive file.

It is also your responsibility to manage the age of your stored data: most of the filesystems are not intended to provide an indefinite archiving service so when a given file or directory is no longer needed, you need to move it to a more appropriate filesystem which may well mean your personal workstation or some other storage system under your control. Moving significant amounts of data between your workstation and one of our systems or between two of our systems should generally be done using Globus.

Note that our storage systems are not for personal use and should only be used to store research data.

When your account is created on a cluster, your home directory will not be entirely empty. It will contain references to your scratch and project spaces through the mechanism of a symbolic link, a kind of shortcut that allows easy access to these other filesystems from your home directory. Note that these symbolic links may appear up to a few hours after you first connect to the cluster. While your home and scratch spaces are unique to you as an individual user, the project space is shared by a research group. This group may consist of those individuals with an account sponsored by a particular faculty member or members of an RAC allocation. A given individual may thus have access to several different project spaces, associated with one or more faculty members, with symbolic links to these different project spaces in the directory projects of your home. Every account has one or many projects. In the folder projects within their home directory, each user has a link to each of the projects they have access to. For users with a single active sponsored role, it is the default project of your sponsor while users with more than one active sponsored role will have a default project that corresponds to the default project of the faculty member with the most sponsored accounts.

All users can check the available disk space and the current disk utilization for the project, home and scratch filesystems with the command line utility diskusage_report, available on our clusters. To use this utility, log into the cluster using SSH, at the command prompt type diskusage_report, and press the Enter key. Below is a typical output of this utility:

# diskusage_report
                   Description                Space           # of files
                 Home (username)         280 kB/47 GB              25/500k
              Scratch (username)         4096 B/18 TB              1/1000k
       Project (def-username-ab)       4096 B/9536 GB              2/500k
          Project (def-username)       4096 B/9536 GB              2/500k

More detailed output is available using the Diskusage Explorer tool.

Storage types[edit]

Unlike your personal computer, our systems will typically have several storage spaces or filesystems and you should ensure that you are using the right space for the right task. In this section we will discuss the principal filesystems available on most of our systems and the intended use of each one along with some of its characteristics.

  • HOME: While your home directory may seem like the logical place to store all your files and do all your work, in general this isn't the case; your home normally has a relatively small quota and doesn't have especially good performance for writing and reading large amounts of data. The most logical use of your home directory is typically source code, small parameter files and job submission scripts.
  • PROJECT: The project space has a significantly larger quota and is well adapted to sharing data among members of a research group since it, unlike the home or scratch, is linked to a professor's account rather than an individual user. The data stored in the project space should be fairly static, that is to say the data are not likely to be changed many times in a month. Otherwise, frequently changing data, including just moving and renaming directories, in project can become a heavy burden on the tape-based backup system.
  • SCRATCH: For intensive read/write operations on large files (> 100 MB per file), scratch is the best choice. However, remember that important files must be copied off scratch since they are not backed up there, and older files are subject to purging. The scratch storage should therefore be used for temporary files: checkpoint files, output from jobs and other data that can easily be recreated. Do not regard SCRATCH as your normal storage! It is for transient files that you can afford to lose.
  • SLURM_TMPDIR: While a job is running, $SLURM_TMPDIR is a unique path to a temporary folder on a local fast filesystem on each compute node reserved for the job. This is the best location to temporarily store large collections of small files (< 1 MB per file). Note that this space is shared between jobs on each node and the total available space depends on the node specifications. Finally, when the job ends, this folder is deleted. A more detailed discussion of using $SLURM_TMPDIR is available at this page.

Project space consumption per user[edit]

While the command diskusage_report gives the space and file count usage per user on home and scratch, it shows the total quota of the group on project. It includes all the files from each member of the group. Since the files that belong to a user could however be anywhere in the project space, it is difficult to obtain correct figures per user and per given project in case a user has access to more than one project. However, users can obtain an estimate of their space and file count use on the entire project space by running the command

lfs quota -u $USER /project

In addition to that, users can obtain an estimate for the number of files in a given directory (and its subdirectories) using the command lfs find, e.g.

lfs find <path to the directory> -type f | wc -l

Best practices[edit]

  • Regularly clean up your data in the scratch and project spaces, because those filesystems are used for huge data collections.
  • Only use text format for files that are smaller than a few megabytes.
  • As far as possible, use scratch and local storage for temporary files. For local storage you can use the temporary directory created by the job scheduler for this, named $SLURM_TMPDIR.
  • If your program must search within a file, it is fastest to do it by first reading it completely before searching.
  • If you no longer use certain files but they must be retained, archive and compress them, and if possible move them to an alternative location like nearline.
  • For more on managing many files, see Handling large collections of files, especially if you are limited by a quota on the number of files.
  • Having any sort of parallel write access to a file stored on a shared filesystem like home, scratch and project is likely to create problems unless you are using a specialized tool such as MPI-IO.
  • If your needs are not well served by the available storage options please contact technical support.

Filesystem quotas and policies[edit]

In order to ensure that there is adequate space for all users, there are a variety of quotas and policy restrictions concerning backups and automatic purging of certain filesystems. By default on our clusters, each user has access to the home and scratch spaces, and each group has access to 1 TB of project space. Small increases in project and scratch spaces are available through our Rapid Access Service (RAS). Larger increases in project spaces are available through the annual Resource Allocation Competition (RAC). You can see your current quota usage for various filesystems on Cedar and Graham using the command diskusage_report.

Filesystem Characteristics
Filesystem Default Quota Lustre-based Backed up Purged Available by Default Mounted on Compute Nodes
Home Space 50 GB and 500K files per user[1] Yes Yes No Yes Yes
Scratch Space 20 TB and 1M files per user Yes No Files older than 60 days are purged.[2] Yes Yes
Project Space 1 TB and 500K files per group[3] Yes Yes No Yes Yes
Nearline Space 2 TB and 5000 files per group Yes Yes No Yes No
  1. This quota is fixed and cannot be changed.
  2. See Scratch purging policy for more information.
  3. Project space can be increased to 10 TB per group by a RAS request. The group's sponsoring PI should write to technical support to make the request.

Starting April 1, 2024, new Rapid Access Service (RAS) policies will allow larger quotas for the project and nearline spaces. For more details, see the "Storage" section at Rapid Access Service. Quota changes larger than those permitted by RAS will require an application to the annual Resource Allocation Competition (RAC).

Filesystem Characteristics
Filesystem Default Quota Lustre-based Backed up Purged Available by Default Mounted on Compute Nodes
Home Space 50 GB and 500K files per user[1] No Yes No Yes Yes
Scratch Space 20 TB and 1M files per user Yes No Files older than 60 days are purged.[2] Yes Yes
Project Space 1 TB and 500K files per group[3] Yes Yes No Yes Yes
Nearline Space 10 TB and 5000 files per group Yes Yes No Yes No
  1. This quota is fixed and cannot be changed.
  2. See Scratch purging policy for more information.
  3. Project space can be increased to 10 TB per group by a RAS request. The group's sponsoring PI should write to technical support to make the request.

Starting April 1, 2024, new Rapid Access Service (RAS) policies will allow larger quotas for project and nearline spaces. For more details, see the "Storage" section at Rapid Access Service. Quota changes larger than those permitted by RAS will require an application to the annual Resource Allocation Competition (RAC).

Filesystem Characteristics
Filesystem Default Quota Lustre-based Backed up Purged Available by Default Mounted on Compute Nodes
Home Space 50 GB and 500K files per user[1] Yes Yes No Yes Yes
Scratch Space 20 TB and 1M files per user Yes No Files older than 60 days are purged.[2] Yes Yes
Project Space 1 TB and 500K files per group[3] Yes Yes No Yes Yes
Nearline Space 1 TB and 5000 files per group Yes Yes No Yes No
  1. This quota is fixed and cannot be changed.
  2. See Scratch purging policy for more information.
  3. Project space can be increased to 10 TB per group by a RAS request. The group's sponsoring PI should write to technical support to make the request.

Starting April 1, 2024, new Rapid Access Service (RAS) policies will allow larger quotas for project and nearline spaces. For more details, see the "Storage" section at Rapid Access Service. Quota changes larger than those permitted by RAS will require an application to the annual Resource Allocation Competition (RAC).

location quota block size expiration time backed up on login nodes on compute nodes
$HOME 100 GB per user 1 MB yes yes read-only
$SCRATCH 25 TB per user (dynamic per group) 16 MB 2 months no yes yes
up to 4 users per group 50TB
up to 11 users per group 125TB
up to 28 users per group 250TB
up to 60 users per group 400TB
above 60 users per group 500TB
$PROJECT by group allocation (RRG or RPP) 16 MB yes yes yes
$ARCHIVE by group allocation dual-copy no no
$BBUFFER 10 TB per user 1 MB very short no yes yes

The backup policy on the home and project space is nightly backups which are retained for 30 days, while deleted files are retained for a further 60 days; note that is entirely distinct from the age limit for purging files from the scratch space. If you wish to recover a previous version of a file or directory, you should contact technical support with the full path for the file(s) and desired version (by date).

See also[edit]