Difference between revisions of "SLURM Active QOS'"

(Created page with "= Active QOS'= Some hardware on CIRCE is provided by research contributors. This hardware is available for use by all CIRCE users by specifying the partition and the "preempt...")
 
 
(19 intermediate revisions by 2 users not shown)
Line 1: Line 1:
= Active QOS'=
= Active QOS'=


Some hardware on CIRCE is provided by research contributors. This hardware is available for use by all CIRCE users by specifying the partition and the "preempt" QOS (example: ''sbatch --partition=mri2016 --qos=preempt ./submit-script.sh''). The caveat however is that as this is contributor hardware, non-contributor jobs running on this partition are subject to preemption.
The following table lists currently configured QOS' available to users on CIRCE. Any QOS which is considered '''"Default"''' does not need to be '''explicitly''' specified in submission syntax. All others must be explicitly specified.


There is a partition-specified grace period (listed above, typically 2 hours) before a contributor’s job(s) will cancel the non-contributors job(s). This means that any user taking advantage of the hardware should have some kind of check-pointing enabled, so that interrupted jobs can be re-submitted without needing to start over.
Research Computing administrators have assigned QOS' due to:
* contribution status
* research need(s)
* time constraints
* access controls
 
Please email {{rchelp}} if you have any questions and/or comments pertaining to currently configured QOS', or if you require access to a QOS listed below.
 
{| class=wikitable
|- style="background-color:#f1edbe;"
|'''QOS'''
|'''Default'''
|'''Description'''
|'''Base Priority'''
|'''Preemptable'''
|'''Preempted by'''
|'''Grace Period'''
|'''Maximum runtime'''
|'''Maximum permitted resources'''
|'''Maximum submitted jobs'''
|'''Accepted on partition(s)'''
|-
|ac
|YES
|Active Contributor.  Applied to parties who have made contributions to the cluster within 4 years.
|500
|NO
|N/A
|N/A
|7 days
|1024 CPU's
|2000
|circe
|-
|bfbsm19
|YES
|College of Mechanical Engineering BFBSM 2019 hardware purchase
|2000
|NO
|N/A
|N/A
|28 days
|260 CPU's
|500
|bfbsm_2019
|-
|cms_ocg
|YES
|College of Marine Science OCG 2019 hardware purchase.
|1000
|NO
|N/A
|N/A
|7 days
|194 CPU's
|500
|cms_ocg
|-
|deadline
|NO
|Applied to users facing critical deadlines.
|15000
|NO
|N/A
|N/A
|3 days
|384 CPU's
|30
|circe
|-
|faculty
|YES
|Applied to all non contributing faculty.
|50
|NO
|N/A
|N/A
|7 days
|2048 CPU's
|1024
|circe
|-
|chbme18
|NO
|Applied to research group associated with chbme_2018 partition.
|500
|NO
|N/A
|N/A
|UNLIMITED
|UNLIMITED
|UNLIMITED
|chbme_2018
|-
|ic
|YES
|Inactive contributor.  Applied to parties who have ever contributed to the cluster.
|400
|NO
|N/A
|N/A
|7 days
|1024 CPU's
|2000
|circe
|-
|interactive
|NO
|Applied to all users for interactive access
|1000
|YES
|hchg
|1 hour
|7 days
|2 CPU's
|2
|hchg
|-
|longrun
|NO
|Applied to users whose job runtime requirements exceed 7 days.
|1
|NO
|N/A
|N/A
|35 days
|384 CPU's
|80
|circe, himem
|-
|memaccess
|NO
|Applied to users whose job memory requirements (vetted) require more than 64 GB of RAM.
|1000
|NO
|N/A
|N/A
|7 days
|UNLIMITED
|100
|himem
|-
|normal
|YES
|Applied to all non contributing, non faculty users.
|1
|NO
|N/A
|N/A
|7 days
|1024 CPU's
|10000
|circe
|-
|openaccess
|No
|Applied to all non contributing, non faculty users of the SNSM 19 grant hardware.
|0
|NO
|N/A
|N/A
|2 days
|100 CPU's
|25
|snsm_itn19
|-
|preempt
|NO
|Applied to all users to allow jobs to run on preemptable partitions.
|500
|YES
|
|2 hours
|7 days
|1024 CPU's
|2000
|bfbsm_2019, cbcs, margres_2020
|-
|preempt_short
|NO
|Applied to all users to allow jobs to run on the simmons_itn18 and muma_2021 partitions.
|500
|YES
|
|.5 hours
|7 days
|1024 CPU's
|2000
|simmons_itn18, muma_2021
|-
|rra
|NO
|Applied to authorized users of the rra partition.
|1000
|NO
|N/A
|N/A
|7 days
|1200 CPU's
|500
|rra
|-
|sim18
|NO
|Applied to research group associated with simmons_itn18 partition.
|1000
|NO
|N/A
|N/A
|UNLIMITED
|432 CPU's
|UNLIMITED
|simmons_itn18
|-
|snsm19
|NO
|Applied to users whose grant funds purchased the SNSM 19 hardware.
|2000
|NO
|N/A
|N/A
|2 days
|400 CPU's, 100 CPU's per job
|50
|snsm_itn19
|-
|snsm19_long
|NO
|Applied to users whose grant funds purchased the SNSM 19 hardware.
|2000
|NO
|N/A
|N/A
|5 days
|40 CPU's and 3 nodes
|50
|snsm_itn19
|-
|trial
|NO
|Applied to potential new users of the system that need to extensively test their code(s).
|0
|NO
|N/A
|N/A
|7 days
|UNLIMITED
|3
|circe
|-
|}

Latest revision as of 21:45, 13 February 2024

Active QOS'

The following table lists currently configured QOS' available to users on CIRCE. Any QOS which is considered "Default" does not need to be explicitly specified in submission syntax. All others must be explicitly specified.

Research Computing administrators have assigned QOS' due to:

  • contribution status
  • research need(s)
  • time constraints
  • access controls

Please email rc-help@usf.edu if you have any questions and/or comments pertaining to currently configured QOS', or if you require access to a QOS listed below.

QOS Default Description Base Priority Preemptable Preempted by Grace Period Maximum runtime Maximum permitted resources Maximum submitted jobs Accepted on partition(s)
ac YES Active Contributor. Applied to parties who have made contributions to the cluster within 4 years. 500 NO N/A N/A 7 days 1024 CPU's 2000 circe
bfbsm19 YES College of Mechanical Engineering BFBSM 2019 hardware purchase 2000 NO N/A N/A 28 days 260 CPU's 500 bfbsm_2019
cms_ocg YES College of Marine Science OCG 2019 hardware purchase. 1000 NO N/A N/A 7 days 194 CPU's 500 cms_ocg
deadline NO Applied to users facing critical deadlines. 15000 NO N/A N/A 3 days 384 CPU's 30 circe
faculty YES Applied to all non contributing faculty. 50 NO N/A N/A 7 days 2048 CPU's 1024 circe
chbme18 NO Applied to research group associated with chbme_2018 partition. 500 NO N/A N/A UNLIMITED UNLIMITED UNLIMITED chbme_2018
ic YES Inactive contributor. Applied to parties who have ever contributed to the cluster. 400 NO N/A N/A 7 days 1024 CPU's 2000 circe
interactive NO Applied to all users for interactive access 1000 YES hchg 1 hour 7 days 2 CPU's 2 hchg
longrun NO Applied to users whose job runtime requirements exceed 7 days. 1 NO N/A N/A 35 days 384 CPU's 80 circe, himem
memaccess NO Applied to users whose job memory requirements (vetted) require more than 64 GB of RAM. 1000 NO N/A N/A 7 days UNLIMITED 100 himem
normal YES Applied to all non contributing, non faculty users. 1 NO N/A N/A 7 days 1024 CPU's 10000 circe
openaccess No Applied to all non contributing, non faculty users of the SNSM 19 grant hardware. 0 NO N/A N/A 2 days 100 CPU's 25 snsm_itn19
preempt NO Applied to all users to allow jobs to run on preemptable partitions. 500 YES 2 hours 7 days 1024 CPU's 2000 bfbsm_2019, cbcs, margres_2020
preempt_short NO Applied to all users to allow jobs to run on the simmons_itn18 and muma_2021 partitions. 500 YES .5 hours 7 days 1024 CPU's 2000 simmons_itn18, muma_2021
rra NO Applied to authorized users of the rra partition. 1000 NO N/A N/A 7 days 1200 CPU's 500 rra
sim18 NO Applied to research group associated with simmons_itn18 partition. 1000 NO N/A N/A UNLIMITED 432 CPU's UNLIMITED simmons_itn18
snsm19 NO Applied to users whose grant funds purchased the SNSM 19 hardware. 2000 NO N/A N/A 2 days 400 CPU's, 100 CPU's per job 50 snsm_itn19
snsm19_long NO Applied to users whose grant funds purchased the SNSM 19 hardware. 2000 NO N/A N/A 5 days 40 CPU's and 3 nodes 50 snsm_itn19
trial NO Applied to potential new users of the system that need to extensively test their code(s). 0 NO N/A N/A 7 days UNLIMITED 3 circe
Retrieved from "https://wiki.rc.usf.edu/index.php?title=SLURM_Active_QOS%27&oldid=2870"