Disk reservation

From Grid5000
Jump to: navigation, search
See also: Storage overview | Storage Manager | Storage5k | Ceph | Local (on nodes) disks reservation
Note.png Note

This tutorial is actively maintained by the Grid'5000 team. If you encounter problems, please report them (see the Support page). Additionally, as it is a wiki page, you are free to make minor corrections yourself if needed. If you would like to suggest a more fundamental change, please contact the Grid'5000 team.

Disk reservation consists in reserving nodes' hard disks, in order to locally store large datasets between your reservations, and avoid needing moving data to nodes at the beginning of each node reservation. Typically, you can reserve disks for several days, store your data on those disks during your first nodes reservation, and then access the data during the subsequent nodes reservations.

The table below shows the cluster compatibility with disk reservation.

Site Cluster Number of nodes Number of reservable disks per node
Lille chifflet 8 3
Nancy grimoire 8 5
Rennes parasilo 28 5
Last generated from the Grid'5000 Reference API on 2018-05-28 (commit 7464e98fc)


How it works

Disk reservation works with jobs of type deploy and jobs of type noop. You can reserve some disks in the long run with a job of type noop. Then, you may reserve a job of type deploy on the same nodes as those where you reserved your disks.

When the job of type deploy starts, the disks you reserved are enabled by the RAID card of the node, and the other disks are disabled. Reserved disks can only be accessed by the user who reserved them (see also Security issues).

Usage

The main commands to reserve disks are given below.

Note.png Note

Note that accessing the data stored on reserved disks on nodes is only possible with reservation of type deploy (oarsub -t deploy ...). Non-deploy jobs do not give access to disks (only the system disk).

The maximum duration of a disk reservation is defined in the Usage Policy.

Reserve disks and nodes at the same time

How to reserve a node with only the main disk (none of the additional disks), on the grimoire cluster
Terminal.png fnancy:
oarsub -I -t deploy -p "cluster='grimoire'" -l /host=1

(no change to the way a node was to be reserved in the past, before the disk reservation mechanism existed.)

How to reserve a node with all its disks
Warning.png Warning

Currently, in conditions where host may be "Absent", "Dead" or "Suspected" while disks resources are "Alive", the created job may only include disk resources but no host (bug #9450). Mind looking at the Gantt diagrams with disk reservations in order to check that you actually get what you requested.

Terminal.png fnancy:
oarsub -I -t deploy -l {"type='disk' or type='default' and disk_reservation_count > 0"}/host=1

(disk_reservation_count is equal to the number of disks which can be reserved on a node.)

How to reserve nodes grimoire-1 and grimoire-2 with one reservable disk per node
Terminal.png fnancy:
oarsub -I -t deploy -p "host in ('grimoire-1.nancy.grid5000.fr','grimoire-2.nancy.grid5000.fr')" -l /host=2+{"type='disk'"}/host=2/disk=1
Note.png Note

Yes, the syntax of the last oarsub command is a bit awkward, so please be careful and mind having:

  • the -p option explicitly set the hosts you want (using "cluster='grimoire'" instead could not insure that you get the disks on the same nodes you will reserve) ;
  • both host= values in the -l option (2 in the example) exactly match the count of hosts in the list you provide in the -p option (grimoire-1.nancy.grid5000.fr and grimoire-2.nancy.grid5000.fr in the example).
  • we do not need to explicitly write "{type='default'}" in the -l option (before the /host=2+, because default is implicit is the type is not set.
See Advanced OAR for more explanation of the oarsub syntax.

Reserve disks and nodes separately

You may, for example, decide to reserve some disks for one week, but the nodes where your disks are located only when you want to carry out an experiment.

First: reserve the disks

Since we want to reserve disks only in a first time, we use the noop job type: with this noop job type, OAR will not try to execute anything on the job resources (which is what we want since disk resources are not capable of executing programs).

(Please mind that Jobs of type noop cannot be interactive: oarsub-I -t noop ... is not supported.)

3 examples:

Reserve two disks on grimoire-1 for one week, starting on 2018-01-01:

Terminal.png fnancy:
oarsub -r "2018-01-01 00:00:00" -t noop -l {"type='disk' and host='grimoire-1.nancy.grid5000.fr'"}/host=1/disk=2,walltime=168

Or reserve the first two disks on grimoire-2:

Terminal.png fnancy:
oarsub -r "2018-01-01 00:00:00" -t noop -l {"type='disk' and host='grimoire-2.nancy.grid5000.fr' and disk in ('sdb.grimoire-2', 'sdc.grimoire-2')"}/host=1/disk=2,walltime=168

Or reserve all disks on two nodes:

Terminal.png fnancy:
oarsub -r "2018-01-01 00:00:00" -t noop -l {"type='disk' and cluster='grimoire'"}/host=2/disk=ALL,walltime=168

Second: reserve the nodes

You can then reserve nodes grimoire-1 and grimoire-2 for 3 hours, in the usual way:

Terminal.png fnancy:
oarsub -I -t deploy -l {"host in ('grimoire-1.nancy.grid5000.fr', 'grimoire-2.nancy.grid5000.fr')"}/host=2,walltime=3

You must respect this order : reserve the disks first, then reserve the nodes. Otherwise the disks you reserved will not be available on your nodes.

Show and use my reserved disks

Gantt diagrams with disk reservations

Reservations of both nodes (processors) and disks are displayed on the following Gantt diagrams:

Lille

Nancy

Rennes

Getting information about disk reservations from OAR and G5K APIs

  • The OAR API shows the properties of each resource of a job. You can retrieve the properties of your reserved disks, such as disk or diskpath:
Terminal.png fnancy:
curl https://api.grid5000.fr/stable/sites/site/internal/oarapi/jobs/job_id/resources.json (or resources.yaml)
  • The Grid'5000 API in version sid also provide some details about disk reservations under the "disks" key of the status and jobs APIs:
Terminal.png fnancy:
curl https://api.grid5000.fr/sid/sites/site/status | json_pp
Terminal.png fnancy:
curl https://api.grid5000.fr/sid/sites/site/jobs/job_id | json_pp


Show disks once connected on the machines

Once connected to a node in a deploy job with one or more disks reserved locally on the node, several tools can be used to manage the disk(s):

  • lsblk will show you the block devices of your disks: sdb, sdc, ... (be careful: sda is the system disk);
  • Commands like fdisk or parted can be used to partition the disk, if needed;
  • mkfs can be used to format the disk.

Mind that the platform provides access to the block devices, but does not manage partitioning nor formatting.

Security issues

The mechanism used to enable/disable disks is designed to avoid mistakes from other users. However, a malicious user could take control of the RAID card, enable any disk, and access or erase your data. Please mind securing your data:

  • Keep a copy (backup) in a safe place if relevant for your data ;
  • If your data is sensitive, mind using cryptographic mechanisms to secure it.

Also, the data on reserved disks is not automatically erased at the end of your job. If you don't want the next user to access it, you have to erase it yourself.

Finally, of course, no backups of data made on the reserved disks are made.