Slurm 作业不能为多个节点请求 GPU 资源

Question

全部。

在我的 Slurm 集群中，当 srun 或 sbatch 作业请求多个节点的资源时，将无法正确提交。

这个 Slurm 集群有 4 个节点，每个节点有 4 个 GPU。

我可以同时使用 4 个 GPU 执行多个作业。

但我无法运行 5 个或更多 GPU 的作业请求。

下面的信息会显示cise3状态为down，这是另一个问题。

错误信息：

sbatch：错误：批处理作业提交失败：请求的节点配置不可用

开始.sh：

#!/bin/bash
#SBATCH -o code20.out
#SBATCH --partition=cup-hpc
#SBATCH --nodes=3
#SBATCH --ntasks-per-node=1
#SBATCH --cpus-per-task=40
#SBATCH --gres=gpu:5
#SBATCH --mem-per-cpu=100mb

source /home/slurm/tensorflow_prj/tf_gpu_cluster/bin/activate
python3 /nfs/code/code20.py

slurm.conf：

NodeName=cise1 NodeAddr=10.18.19.191 CPUs=40 RealMemory=94887 Sockets=2 CoresPerSocket=10 ThreadsPerCore=2 State=UNKNOWN Gres=gpu:rtx4000:4
NodeName=cise2 NodeAddr=10.18.19.107 CPUs=40 RealMemory=94889 Sockets=2 CoresPerSocket=10 ThreadsPerCore=2 State=UNKNOWN Gres=gpu:rtx4000:4
NodeName=cise3 NodeAddr=10.18.19.47  CPUs=40 RealMemory=94889 Sockets=2 CoresPerSocket=10 ThreadsPerCore=2 State=UNKNOWN Gres=gpu:rtx4000:4
NodeName=cise4 NodeAddr=10.18.19.183 CPUs=40 RealMemory=94889 Sockets=2 CoresPerSocket=10 ThreadsPerCore=2 State=UNKNOWN Gres=gpu:rtx4000:4
PartitionName=cup-hpc Nodes=cise[1-4] Default=YES MaxTime=INFINITE State=UP

gres.conf：

# Configure support for four GPUs (with MPS), plus bandwidth
AutoDetect=nvml
Name=gpu File=/dev/nvidia0
Name=gpu File=/dev/nvidia1
Name=gpu File=/dev/nvidia2
Name=gpu File=/dev/nvidia3

信息：

[root@localhost nfs]# sinfo
PARTITION AVAIL  TIMELIMIT  NODES  STATE NODELIST
cup-hpc*     up   infinite      1  down* cise3
cup-hpc*     up   infinite      3   idle cise[1-2,4]

scontrol 显示节点：

[root@localhost nfs]# scontrol show nodes
NodeName=cise1 Arch=x86_64 CoresPerSocket=10
   CPUAlloc=0 CPUTot=40 CPULoad=0.01
   AvailableFeatures=(null)
   ActiveFeatures=(null)
   Gres=gpu:rtx4000:4
   NodeAddr=10.18.19.191 NodeHostName=cise1 Version=20.02.1
   OS=Linux 4.18.0-80.el8.x86_64 #1 SMP Tue Jun 4 09:19:46 UTC 2019
   RealMemory=94887 AllocMem=0 FreeMem=83727 Sockets=2 Boards=1
   State=IDLE ThreadsPerCore=2 TmpDisk=0 Weight=1 Owner=N/A MCS_label=N/A
   Partitions=cup-hpc
   BootTime=2020-04-13T08:34:13 SlurmdStartTime=2020-04-17T14:49:20
   CfgTRES=cpu=40,mem=94887M,billing=40
   AllocTRES=
   CapWatts=n/a
   CurrentWatts=0 AveWatts=0
   ExtSensorsJoules=n/s ExtSensorsWatts=0 ExtSensorsTemp=n/s


NodeName=cise2 Arch=x86_64 CoresPerSocket=10
   CPUAlloc=0 CPUTot=40 CPULoad=0.00
   AvailableFeatures=(null)
   ActiveFeatures=(null)
   Gres=gpu:rtx4000:4
   NodeAddr=10.18.19.107 NodeHostName=cise2 Version=20.02.1
   OS=Linux 4.18.0-80.el8.x86_64 #1 SMP Tue Jun 4 09:19:46 UTC 2019
   RealMemory=94889 AllocMem=0 FreeMem=83405 Sockets=2 Boards=1
   State=IDLE ThreadsPerCore=2 TmpDisk=0 Weight=1 Owner=N/A MCS_label=N/A
   Partitions=cup-hpc
   BootTime=2020-04-13T08:33:51 SlurmdStartTime=2020-04-17T14:49:33
   CfgTRES=cpu=40,mem=94889M,billing=40
   AllocTRES=
   CapWatts=n/a
   CurrentWatts=0 AveWatts=0
   ExtSensorsJoules=n/s ExtSensorsWatts=0 ExtSensorsTemp=n/s


NodeName=cise3 Arch=x86_64 CoresPerSocket=10
   CPUAlloc=0 CPUTot=40 CPULoad=0.00
   AvailableFeatures=(null)
   ActiveFeatures=(null)
   Gres=gpu:rtx4000:4
   NodeAddr=10.18.19.47 NodeHostName=cise3 Version=20.02.1
   OS=Linux 4.18.0-80.el8.x86_64 #1 SMP Tue Jun 4 09:19:46 UTC 2019
   RealMemory=94889 AllocMem=0 FreeMem=83456 Sockets=2 Boards=1
   State=DOWN* ThreadsPerCore=2 TmpDisk=0 Weight=1 Owner=N/A MCS_label=N/A
   Partitions=cup-hpc
   BootTime=2020-04-13T08:31:48 SlurmdStartTime=2020-04-17T15:10:16
   CfgTRES=cpu=40,mem=94889M,billing=40
   AllocTRES=
   CapWatts=n/a
   CurrentWatts=0 AveWatts=0
   ExtSensorsJoules=n/s ExtSensorsWatts=0 ExtSensorsTemp=n/s
   Reason=Not responding [slurm@2020-04-17T15:17:58]

NodeName=cise4 Arch=x86_64 CoresPerSocket=10
   CPUAlloc=0 CPUTot=40 CPULoad=0.00
   AvailableFeatures=(null)
   ActiveFeatures=(null)
   Gres=gpu:rtx4000:4
   NodeAddr=10.18.19.183 NodeHostName=cise4 Version=20.02.1
   OS=Linux 4.18.0-80.el8.x86_64 #1 SMP Tue Jun 4 09:19:46 UTC 2019
   RealMemory=94889 AllocMem=0 FreeMem=83432 Sockets=2 Boards=1
   State=IDLE ThreadsPerCore=2 TmpDisk=0 Weight=1 Owner=N/A MCS_label=N/A
   Partitions=cup-hpc
   BootTime=2020-04-13T08:36:40 SlurmdStartTime=2020-04-17T14:49:23
   CfgTRES=cpu=40,mem=94889M,billing=40
   AllocTRES=
   CapWatts=n/a
   CurrentWatts=0 AveWatts=0
   ExtSensorsJoules=n/s ExtSensorsWatts=0 ExtSensorsTemp=n/s

Answer 1

slurm gres 规范是每个节点的请求。 您的工作目前需要 3 个节点，每个节点有 5 个 GPU。

资料来源： https://slurm.schedmd.com/gres.html#Running_Jobs