The University of Arizona
    For questions, please open a UAService ticket and assign to the Tools Team.
Page tree

Versions Compared

Key

  • This line was added.
  • This line was removed.
  • Formatting was changed.

Page Banner
imagehttps://public.confluence.arizona.edu/download/attachments/93159830/disk.jpg?api=v2
titleStorage

Excerpt Include
Getting Help
Getting Help
nopaneltrue


Panel
borderColor#9c9fb5
bgColor#fafafe
borderWidth2
borderStyledouble

Where Should I Store My Data?

  1. Data undergoing active analyses should be stored in HPC's local High Performance Storage (Tier 1).

  2.  Large amounts of data that could be considered "warm" can be stored at reasonable rates on our Rental Storage.

  3. Research data not requiring immediate access should be stored in General Research Data Storage (Tier 2)
    For example:
    1. Large datasets where only subsets are actively being analyzed
    2. Results no longer requiring immediate access
    3. Backups (highly encouraged!)

  4. Data no longer involved in ongoing analyses that need long-term archiving should be stored in Long term Research Storage (Tier 3).




Panel
borderColor#9c9fb5
bgColor#fcfcfc
titleColor#fcfcfc
titleBGColor#021D61
borderStylesolid
titleContents

Table of Contents
maxLevel2



Panel
borderColor#9c9fb5
bgColor#fafafe
borderWidth2
borderStyledouble

Storage Option Summary


PurposeCapacityCostRestricted data?AccessDurationBackup








Primary StorageResearch data. Supports compute. Directly attached to HPC/home 50GB /groups 500GB /xdisk 20TBFreeNot for restricted dataDirectly mounted to HPC. Also uses Globus and DTNsLong term. Aligns with HPC purchase cycleNo
Rental StorageResearch data. Large datasets. Typically for staging to HPCRented per Terabyte per yearRental rate: $47.35 per TB per yearNot for restricted dataUses Globus and DTNs. Copy data to PrimaryLong term. Aligns with HPC purchase cycleNo
Tier 2Typically research data. Unused data is archived15GB to TB'sTier-based system. First 1TB of active data and archival data are free. Active data > 1TB is paid.Not for restricted dataUses Globus and AWS command line interfaceTypically long term since use of Glacier is free and slowArchival
ReDataResearch data. Managed by UA LibrariesQuota systemFreeNot for restricted dataLogin and fill out fields, then uploadLonger than 10 yearsNo

Soteria
HIPAA

Secure data enclaveIndividual requestsFree upon qualificationRestricted data; HIPAA, ePHIHIPAA training required, followed by request processLong termNo
BoxGeneral data50GBFreeNot for restricted dataBrowserLong termNo
Google DriveGeneral data15GBFree. Google rates for amounts > 15GBNot for restricted dataBrowserUnlimited usage expires March 1, 2023No





Panel
borderColor#9c9fb5
bgColor#fafafe
borderWidth2
borderStyledouble

HPC High Performance Storage (Tier 1)

Warning

Data stored on HPC are not backed up! All data on this storage should be backed up elsewhere by UA researchers, preferably in three places and two formats. 


Tip

We strongly recommend that you do some regular housekeeping of your allocated space. Millions of files are hard to keep organized and even more difficult to migrate. Archiving or using a tool like tar will help keep our disk arrays efficient and potentially free up more space for you to use.

Summary

Every user has access to individual and group storage on the system where they can store data for active analyses as summarized below:

PathDescriptionQuotaDuration
/home/uxx/netidAn individual storage allocation provided for every HPC user50GB
/groups/pi_netidA communal storage allocation provided for every research group500GB
/xdisk/pi_netidTemporary communal storage provided for every group. 200GB-20TBUp to 300 days
/tmpLocal storage available on individual compute nodes. < 800GB to 1.4TBOnly accessible for the duration of a job's run.

Checking your Storage Quota and Usage


Deck of Cards
startHiddenfalse
idChecking your Quota


Card
idcli
labelCommand Line
titleCheck your quota on the command line

Command Line

To check your storage usage, use the command uquota. For example:

Code Block
languagebash
themeMidnight
(puma) [netid@junonia ~]$ uquota
                                            used  soft limit  hard limit
/groups/pi_netid                            6.6G      500.0G      500.0G
/home                                      37.1G       50.0G       50.0G
/xdisk/pi_netid                            12.9G        9.8T        9.8T



Card
iduser-portal
labelUser Portal
titleCheck your quota in the user portal

You can check your storage allocation through our online user portal by navigating to the Storage tab and clicking Check Disk Quotas:


xdisk

Deck of Cards
startHiddenfalse
idxdisk
loopCardstrue


Card
defaulttrue
idoverview
labelOverview
titlexdisk overview

Overview

Tip

Important /xdisk Basics

  • xdisks are temporary storage allocations available to each research group. No storage on HPC is designed to archive or persist data.
  • Only faculty members (PIs) may request, alter, or delete an allocation from the command line. Members of their research group may be given management rights allowing them to manage their xdisk through our web portal.
  • The maximum lifespan of an xdisk is 300 days. Allocations cannot be extended past the 300 day maximum.
  • Groups may only have one active xdisk at a time.
  • When an xdisk expires, the contents are deleted. 
  • Once an xdisk is deleted or expires, a new one may be immediately requested.
  • xdisks are not backed up.
  • Users must remove their data from HPC before their xdisk expires. We strongly recommend starting the backup process early.   


Warning

xdisk allocations are not backed up. It is the user's responsibility to save files stored in xdisk to alternate storage locations for backup and archive purposes. See Tier 2 Storage for more information on options for backing up your data. 

What is xdisk?

xdisk is a temporary storage allocation available to all PIs and offers up to 20 TB of usable space for their group for up to 300 days. A PI can request an allocation either via the command line or through our web portal (no paperwork necessary!). Once an xdisk allocation is created, it is immediately available for use. 

Because xdisk allocations are temporary, they will expire as soon as their time limit is reached. Warnings will be sent to every group member at their netid@arizona.edu addresses beginning one week before the expiration. It is the group's responsibility to renew xdisk allocations or copy files to an alternate storage location prior to the expiration date. Once an xdisk allocation expires, everything in it is permanently deleted. PI's may request a new xdisk allocation immediately after their previous one has expired. 



Card
idrequest
labelRequesting an xdisk Space
titleRequest an xdisk space

Requesting an xdisk Space

Faculty members (PIs) or their designated xdisk delegates are able to request, alter, extend, and delete an xdisk allocation from the web portal under the storage tab: https://portal.hpc.arizona.edu/portal/

To request a new allocation, select Manage XDISK, fill in the form, and submit.

Image RemovedImage Added


Card
idmodify
labelModifying an Existing Allocation
titleModify an xdisk space

Modifying an Existing Allocation

Faculty members (PIs) or their designated storage delegates are able to modify existing xdisk allocations through the web portal: https://portal.hpc.arizona.edu/portal/

To do this, navigate to the Storage tab and select Manage XDISK

Image Added

In the web form, enter the new size and time allocations needed for your allocation. The maximum size (in GB) allowed is 20000 and the maximum time limit is 300 days.

Image Added

To save the changes, click Ok.


Card
idcli-commands
labelCLI Commands
titleWorking with xdisk on the command line

xdisk CLI

xdisk is a locally written utility for PI's to create, delete, resize, and expire (renew) xdisk allocations. This functionality is usable by PIs only.

Xdisk FunctionInformationCommandExamples
Display xdisk helpCommands given in brackets are optional. If left blank, you will get system defaults.

$ xdisk -c help

$ xdisk -c help
/usr/bin/xdisk -c [query|create|delete|expire|size] [-d days] [-m size]

View current informationCheck current allocation size, location, and expiration date.

$ xdisk -c query


$ xdisk -c query
XDISK on host: ericidle.hpc.arizona.edu
Current xdisk allocation for <netid>:
Disk location: /xdisk/<netid>
Allocated size: 200GB
Creation date: 3/10/2020 Expiration date: 6/8/2020
Max days: 45    Max size: 1000GB

Create an xdisk

Grants an xdisk allocation. 

Max Size: 20000 GB

Max Days: 300

$ xdisk -c create -m [size in gb] -d [days]

$ xdisk -c create -m 300 -d 30
Your create request of 300 GB for 30 days was successful.
Your space is in /xdisk/<netid>

Extend the xdisk timePrior to its expiration, if your xdisk's time is under the 300 days, you may increase it until the 300 day limit is reached.

$ xdisk -c expire -d [days]

$ xdisk -c expire -d 15
Your extension of 15 days was successfully processed

Resize an xdisk allocation

You may resize your allocation by specifying the increase/decrease in gb.

To reduce the size, use a negative sign, "-

$ xdisk -c size -m [size in gb]

$ # Assuming an initial xdisk allocation size of 200 gb
$ xdisk -c size -m 200
XDISK on host: ericidle.hpc.arizona.edu
Your resize to 400GB was successful
$ xdisk -c size -m -100
XDISK on host: ericidle.hpc.arizona.edu
Your resize to 300GB was successful

Delete an xdisk allocationPermanently deletes your current xdisk allocation. Be sure to remove any important data before deleting.

$ xdisk -c delete

$ xdisk -c delete
Your delete request has been processed



Card
iddelegate
labelDelegating xdisk Management
titleDelegating xdisk management rights

Delegating xdisk Management Rights

Warning

When a user is added as a delegate, it allows them to manage group storage on their PI's behalf through the user portal. It will still not be possible for the delegate to manage storage via the CLI interface.

PIs can delegate xdisk management rights. To add a group member as a delegate, the PI needs to click on Manage Delegates link on the home page of the portal:

Once a group member has been added, they can manage their group's xdisk through the web portal. To do this, they should log into our web portal, click the Switch User link, and enter their PI's NetID. They can then manage their group's space under the Storage tab.


Card
idfaqs
labelFAQs
titlexdisk FAQs

Excerpt Include
xdisk
xdisk
nopaneltrue





Panel
borderColor#9c9fb5
bgColor#fafafe
borderWidth2
borderStyledouble

Rental Storage

This service enables researchers to rent storage on an on-site data array located in the UITS research data center and networked near our HPC systems to enable efficient data transfer to/from the HPC.

Funded by RII, this new service is immediately available to any faculty researcher and can be accessed through the HPC user portal.

Details on the service:

  • The first-year rate is $94.50 per TB, and RII will provide matching funds for first-year allocations to make the actual first-year cost to researchers $47.35. These matching funds will be applied automatically.
  • The ongoing rate after year one is $47.35 per TB per year.
  • Researchers must provide a KFS account for this service, which will be charged at the end of the academic year (June 2023)
  • Your space will be mounted as /rental/netid and is mounted on the data transfer nodes
  • You can use Globus to move data that is external to the data center
  • You can use scp, sftp or Globus to move data to and from HPC resources 

More information especially on Getting Started is found at this page

Warning

This service is not intended for controlled or regulated research data, such as HIPAA/ePHI, ITAR, or CUI


Warning

Rental storage is not backed up. It is the user's responsibility to save files stored in xdisk to alternate storage locations for backup and archive purposes. See Tier 2 Storage for more information on options for backing up your data. 




Panel
borderColor#9c9fb5
bgColor#fafafe
borderWidth2
borderStyledouble

General Research Data Storage (Tier 2)

Note
titleGoogle Drive Storage Notice
Free unlimited Google Drive storage will be going away for usage greater than 15GB, and UITS would like to migrate users off by April 2023. As a result, we will be transitioning to Amazon Web Services (AWS) S3 as a Tier 2 option. We will continue to support researchers using Google Drive during this transition.

Research Technologies in partnership with UITS is implementing an Amazon Web Services (AWS) S3 rental storage solution. This service provides researchers with an S3 account which is managed by AWS Intelligent Tiering. After 90 days of nonuse, data will be moved to Glacier. After 90 additional days, it will be moved to Deep Glacier. There will be no charge for data stored at either Glacier level, nor for any transfer charges. The data can be retrieved at any time, although it will take a while. 

For information on setting up and using an S3 account, see: Tier 2 Storage

For information on Google Drive, see: Google Drive




Panel
borderColor#9c9fb5
bgColor#fafafe
borderWidth2
borderStyledouble

Long term Research Storage (Tier 3)

Individual groups are responsible for managing and archiving their data. Some options for data archival include:





Panel
borderColor#9c9fb5
bgColor#fafafe
borderWidth2
borderStyledouble

NIH Data Management and Sharing Policy

The NIH has issued a new data management and sharing policy, effective January 25, 2023. The university libraries now offers a comprehensive guide for how to navigate these policies and what they mean for you.

What's new about the 2023 NIH Data Management and Sharing Policy?

Previously, the NIH only required grants with $500,000 per year or more in direct costs to provide a brief explanation of how and when data resulting from the grant would be shared.

The 2023 policy is entirely new. Beginning in 2023, ALL grant applications or renewals that generate Scientific Data must now include a robust and detailed plan for how you will manage and share data during the entire funded period. This includes information on data storage, access policies/procedures, preservation, metadata standards, distribution approaches, and more. You must provide this information in a data management and sharing plan (DMSP). The DMSP is similar to what other funders call a data management plan (DMP).

The DMSP will be assessed by NIH Program Staff (though peer reviewers will be able to comment on the proposed data management budget). The Institute, Center, or Office (ICO)-approved plan becomes a Term and Condition of the Notice of Award.