CRC provides a few helper scripts that are intended to make the user experience simpler. These include
Checking disk quota with crc-quota
[username@login1 ~]$ crc-quota User: 'username' -> ihome: 70.11 GB / 75.0 GB Group: 'groupname' -> bgfs: 35.91 GB / 5.0 TB
View your group's SLURM allocation details with crc-usage
. Using this command alone will show the details for your user account's default allocation.
[username@login1 ~] : crc-usage +------------------------------------------------------------------------+ | MyUserGroup Proposal Information | +----------------------------+--------------------------+----------------+ | Proposal End Date: | 05/04/2024 | | +----------------------------+--------------------------+----------------+ | Proposal ID: | 897 | | +----------------------------+--------------------------+----------------+ | | | | +----------------------------+--------------------------+----------------+ | Cluster: SMP | Total SUs: 35000 | | +----------------------------+--------------------------+----------------+ | User1 | 128 | N/A | | User2 | 5000 | 14 | +----------------------------+--------------------------+----------------+ | Overall for SMP | 5128 | 0 | +----------------------------+--------------------------+----------------+ | | | | +----------------------------+--------------------------+----------------+ | Cluster: GPU | Total SUs: 25000 | | +----------------------------+--------------------------+----------------+ | | | | +----------------------------+--------------------------+----------------+ | Cluster: HTC | Total SUs: 25000 | | +----------------------------+--------------------------+----------------+ | User | SUs Used | % Used | +----------------------------+--------------------------+----------------+ | User1 | 128 | N/A | +----------------------------+--------------------------+----------------+ | Overall for HTC | 128 | 0 | +----------------------------+--------------------------+----------------+ | | | | +----------------------------+--------------------------+----------------+ | Floating SUs | SUs Remaining | % Used | +----------------------------+--------------------------+----------------+ | *Floating SUs | | | | are applied on | | | | any cluster to | 0* | 0 | | cover usage above | | | | Total SUs | | | +----------------------------+--------------------------+----------------+ | Aggregate Usage | 0 | | +----------------------------+--------------------------+----------------+
Look for available resources across the clusters with crc-idle
.
[username@login1 ~]$ crc-idle Cluster: smp, Partition: smp ============================ 2 nodes w/ 1 idle cores 5 nodes w/ 2 idle cores 1 nodes w/ 3 idle cores 9 nodes w/ 4 idle cores 2 nodes w/ 5 idle cores 11 nodes w/ 6 idle cores 30 nodes w/ 7 idle cores 35 nodes w/ 8 idle cores 1 nodes w/ 9 idle cores 11 nodes w/ 12 idle cores 4 nodes w/ 15 idle cores 1 nodes w/ 16 idle cores 1 nodes w/ 18 idle cores 1 nodes w/ 21 idle cores 1 nodes w/ 22 idle cores 20 nodes w/ 23 idle cores Cluster: smp, Partition: high-mem ================================= 6 nodes w/ 8 idle cores 2 nodes w/ 12 idle cores Cluster: smp, Partition: legacy =============================== 1 nodes w/ 1 idle cores 1 nodes w/ 8 idle cores Cluster: gpu, Partition: gtx1080 ================================ 3 nodes w/ 1 idle GPUs 1 nodes w/ 2 idle GPUs 4 nodes w/ 3 idle GPUs 4 nodes w/ 4 idle GPUs Cluster: gpu, Partition: titanx =============================== 1 nodes w/ 1 idle GPUs 1 nodes w/ 2 idle GPUs 1 nodes w/ 3 idle GPUs 3 nodes w/ 4 idle GPUs Cluster: gpu, Partition: k40 ============================ 1 nodes w/ 2 idle GPUs Cluster: gpu, Partition: v100 ============================= No idle GPUs Cluster: mpi, Partition: opa ============================ No idle cores Cluster: mpi, Partition: opa-high-mem ===================================== No idle cores Cluster: mpi, Partition: ib =========================== 14 nodes w/ 20 idle cores Cluster: htc, Partition: htc ============================ 2 nodes w/ 2 idle cores 1 nodes w/ 5 idle cores 1 nodes w/ 6 idle cores 1 nodes w/ 10 idle cores 3 nodes w/ 11 idle cores 1 nodes w/ 12 idle cores 20 nodes w/ 16 idle cores 4 nodes w/ 24 idle cores 1 nodes w/ 25 idle cores 1 nodes w/ 37 idle cores 5 nodes w/ 48 idle cores
You can request an interactive session on a compute-node with crc-interactive
[username@login1 ~]$ crc-interactive --help crc-interactive -- An interactive Slurm helper Usage: crc-interactive (-s | -g | -m | -i | -d) [-hvzo] [-t <time>] [-n <num-nodes>] [-p <partition>] [-c <num-cores>] [-u <num-gpus>] [-r <res-name>] [-b <memory>] [-a <account>] [-l <license>] [-f <feature>] Positional Arguments: -s --smp Interactive job on smp cluster -g --gpu Interactive job on gpu cluster -m --mpi Interactive job on mpi cluster -i --invest Interactive job on invest cluster -d --htc Interactive job on htc cluster Options: -h --help Print this screen and exit -v --version Print the version of crc-interactive -t --time <time> Run time in hours, 1 <= time <= 12 [default: 1] -n --num-nodes <num-nodes> Number of nodes [default: 1] -p --partition <partition> Specify non-default partition -c --num-cores <num-cores> Number of cores per node [default: 1] -u --num-gpus <num-gpus> Used with -g only, number of GPUs [default: 0] -r --reservation <res-name> Specify a reservation name -b --mem <memory> Memory in GB -a --account <account> Specify a non-default account -l --license <license> Specify a license -f --feature <feature> Specify a feature, e.g. `ti` for GPUs -z --print-command Simply print the command to be run -o --openmp Run using OpenMP style submission [username@login1 ~]$ crc-interactive -g -p titanx -n 1 -c 1 -u 1 -t 12 srun: job 260065 queued and waiting for resources srun: job 260065 has been allocated resources [username@gpu-stage06 ~]$ nvidia-smi Wed Jan 26 08:42:04 2022 +-----------------------------------------------------------------------------+ | NVIDIA-SMI 460.32.03 Driver Version: 460.32.03 CUDA Version: 11.2 | |-------------------------------+----------------------+----------------------+ | GPU Name Persistence-M| Bus-Id Disp.A | Volatile Uncorr. ECC | | Fan Temp Perf Pwr:Usage/Cap| Memory-Usage | GPU-Util Compute M. | | | | MIG M. | |===============================+======================+======================| | 0 GeForce GTX TIT... On | 00000000:02:00.0 Off | N/A | | 48% 82C P2 236W / 250W | 794MiB / 12212MiB | 99% Default | | | | N/A | +-------------------------------+----------------------+----------------------+ | 1 GeForce GTX TIT... On | 00000000:03:00.0 Off | N/A | | 22% 28C P8 16W / 250W | 1MiB / 12212MiB | 0% Default | | | | N/A | +-------------------------------+----------------------+----------------------+ | 2 GeForce GTX TIT... On | 00000000:81:00.0 Off | N/A | | 22% 28C P8 15W / 250W | 1MiB / 12212MiB | 0% Default | | | | N/A | +-------------------------------+----------------------+----------------------+ | 3 GeForce GTX TIT... On | 00000000:82:00.0 Off | N/A | | 22% 27C P8 14W / 250W | 1MiB / 12212MiB | 0% Default | | | | N/A | +-------------------------------+----------------------+----------------------+ +-----------------------------------------------------------------------------+ | Processes: | | GPU GI CI PID Type Process name GPU Memory | | ID ID Usage | |=============================================================================| | 0 N/A N/A 23796 C pmemd.cuda 790MiB | +-----------------------------------------------------------------------------+ [username@gpu-stage06 ~]$ exit exit [username@login1 ~]$
There are a few other helper scripts that you can see by typing crc-
followed two strokes of the tab
key
[username@login1 ~]$ crc- crc-idle crc-job-stats crc-quota crc-squeue crc-usage crc-interactive crc-proposal-end crc-scancel crc-sinfo crc-sus [username@login1 ~]$ crc-
crc-job-stats
- Include at the bottom of a job script, outputs the details of the job after completion
crc-squeue
- Show details for active jobs submitted by your user
crc-scancel
- Cancel a job by job ID from crc-squeue
crc-proposal-end
- Outputs the end date of your user's default allocation
crc-sus
- Show a concise view of the service units awarded on each cluster
crc-show-config
- Show configuration information about the partitions for each cluster
crc-sinfo
- Show the status of the partitions of each cluster and their nodes
The best way to get help on a specific issue is to submit a https://crc.pitt.edu/submit-ticket. You should log in to the CRC website using your Pitt credentials first.